Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,43 @@
+---
+base_model: princeton-nlp/gemma-2-9b-it-SimPO
+tags:
+- alignment-handbook
+- generated_from_trainer
+- mlx
+datasets:
+- princeton-nlp/gemma2-ultrafeedback-armorm
+license: mit
+pipeline_tag: text-generation
+library_name: mlx
+model-index:
+- name: princeton-nlp/gemma-2-9b-it-SimPO
+  results: []
+---
+
+# mlx-community/gemma-2-9b-it-SimPO-mixed-3-6-bit
+
+This model [mlx-community/gemma-2-9b-it-SimPO-mixed-3-6-bit](https://huggingface.co/mlx-community/gemma-2-9b-it-SimPO-mixed-3-6-bit) was
+converted to MLX format from [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO)
+using mlx-lm version **0.26.0**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/gemma-2-9b-it-SimPO-mixed-3-6-bit")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

config.json

@@ -0,0 +1,2823 @@
+{
+    "architectures": [
+        "Gemma2ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": 50.0,
+    "bos_token_id": 2,
+    "cache_implementation": "hybrid",
+    "eos_token_id": 1,
+    "final_logit_softcapping": 30.0,
+    "head_dim": 256,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 8192,
+    "model_type": "gemma2",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 42,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "model.embed_tokens": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.0.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.0.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.0.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.0.self_attn.rope": false,
+        "model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.0.input_layernorm": false,
+        "model.layers.0.pre_feedforward_layernorm": false,
+        "model.layers.0.post_feedforward_layernorm": false,
+        "model.layers.0.post_attention_layernorm": false,
+        "model.layers.1.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.1.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.1.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.1.self_attn.rope": false,
+        "model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.1.input_layernorm": false,
+        "model.layers.1.pre_feedforward_layernorm": false,
+        "model.layers.1.post_feedforward_layernorm": false,
+        "model.layers.1.post_attention_layernorm": false,
+        "model.layers.2.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.2.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.2.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.2.self_attn.rope": false,
+        "model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.2.input_layernorm": false,
+        "model.layers.2.pre_feedforward_layernorm": false,
+        "model.layers.2.post_feedforward_layernorm": false,
+        "model.layers.2.post_attention_layernorm": false,
+        "model.layers.3.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.3.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.3.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.3.self_attn.rope": false,
+        "model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.3.input_layernorm": false,
+        "model.layers.3.pre_feedforward_layernorm": false,
+        "model.layers.3.post_feedforward_layernorm": false,
+        "model.layers.3.post_attention_layernorm": false,
+        "model.layers.4.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.4.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.4.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.4.self_attn.rope": false,
+        "model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.4.input_layernorm": false,
+        "model.layers.4.pre_feedforward_layernorm": false,
+        "model.layers.4.post_feedforward_layernorm": false,
+        "model.layers.4.post_attention_layernorm": false,
+        "model.layers.5.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.self_attn.rope": false,
+        "model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.input_layernorm": false,
+        "model.layers.5.pre_feedforward_layernorm": false,
+        "model.layers.5.post_feedforward_layernorm": false,
+        "model.layers.5.post_attention_layernorm": false,
+        "model.layers.6.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.self_attn.rope": false,
+        "model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.input_layernorm": false,
+        "model.layers.6.pre_feedforward_layernorm": false,
+        "model.layers.6.post_feedforward_layernorm": false,
+        "model.layers.6.post_attention_layernorm": false,
+        "model.layers.7.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.7.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.7.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.7.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.7.self_attn.rope": false,
+        "model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.7.input_layernorm": false,
+        "model.layers.7.pre_feedforward_layernorm": false,
+        "model.layers.7.post_feedforward_layernorm": false,
+        "model.layers.7.post_attention_layernorm": false,
+        "model.layers.8.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.self_attn.rope": false,
+        "model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.input_layernorm": false,
+        "model.layers.8.pre_feedforward_layernorm": false,
+        "model.layers.8.post_feedforward_layernorm": false,
+        "model.layers.8.post_attention_layernorm": false,
+        "model.layers.9.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.self_attn.rope": false,
+        "model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.input_layernorm": false,
+        "model.layers.9.pre_feedforward_layernorm": false,
+        "model.layers.9.post_feedforward_layernorm": false,
+        "model.layers.9.post_attention_layernorm": false,
+        "model.layers.10.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.10.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.10.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.10.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.10.self_attn.rope": false,
+        "model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.10.input_layernorm": false,
+        "model.layers.10.pre_feedforward_layernorm": false,
+        "model.layers.10.post_feedforward_layernorm": false,
+        "model.layers.10.post_attention_layernorm": false,
+        "model.layers.11.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.self_attn.rope": false,
+        "model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.input_layernorm": false,
+        "model.layers.11.pre_feedforward_layernorm": false,
+        "model.layers.11.post_feedforward_layernorm": false,
+        "model.layers.11.post_attention_layernorm": false,
+        "model.layers.12.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.self_attn.rope": false,
+        "model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.input_layernorm": false,
+        "model.layers.12.pre_feedforward_layernorm": false,
+        "model.layers.12.post_feedforward_layernorm": false,
+        "model.layers.12.post_attention_layernorm": false,
+        "model.layers.13.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.13.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.13.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.13.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.13.self_attn.rope": false,
+        "model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.13.input_layernorm": false,
+        "model.layers.13.pre_feedforward_layernorm": false,
+        "model.layers.13.post_feedforward_layernorm": false,
+        "model.layers.13.post_attention_layernorm": false,
+        "model.layers.14.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.self_attn.rope": false,
+        "model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.input_layernorm": false,
+        "model.layers.14.pre_feedforward_layernorm": false,
+        "model.layers.14.post_feedforward_layernorm": false,
+        "model.layers.14.post_attention_layernorm": false,
+        "model.layers.15.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.self_attn.rope": false,
+        "model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.input_layernorm": false,
+        "model.layers.15.pre_feedforward_layernorm": false,
+        "model.layers.15.post_feedforward_layernorm": false,
+        "model.layers.15.post_attention_layernorm": false,
+        "model.layers.16.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.16.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.16.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.16.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.16.self_attn.rope": false,
+        "model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.16.input_layernorm": false,
+        "model.layers.16.pre_feedforward_layernorm": false,
+        "model.layers.16.post_feedforward_layernorm": false,
+        "model.layers.16.post_attention_layernorm": false,
+        "model.layers.17.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.self_attn.rope": false,
+        "model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.input_layernorm": false,
+        "model.layers.17.pre_feedforward_layernorm": false,
+        "model.layers.17.post_feedforward_layernorm": false,
+        "model.layers.17.post_attention_layernorm": false,
+        "model.layers.18.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.self_attn.rope": false,
+        "model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.input_layernorm": false,
+        "model.layers.18.pre_feedforward_layernorm": false,
+        "model.layers.18.post_feedforward_layernorm": false,
+        "model.layers.18.post_attention_layernorm": false,
+        "model.layers.19.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.19.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.19.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.19.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.19.self_attn.rope": false,
+        "model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.19.input_layernorm": false,
+        "model.layers.19.pre_feedforward_layernorm": false,
+        "model.layers.19.post_feedforward_layernorm": false,
+        "model.layers.19.post_attention_layernorm": false,
+        "model.layers.20.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.self_attn.rope": false,
+        "model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.input_layernorm": false,
+        "model.layers.20.pre_feedforward_layernorm": false,
+        "model.layers.20.post_feedforward_layernorm": false,
+        "model.layers.20.post_attention_layernorm": false,
+        "model.layers.21.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.self_attn.rope": false,
+        "model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.input_layernorm": false,
+        "model.layers.21.pre_feedforward_layernorm": false,
+        "model.layers.21.post_feedforward_layernorm": false,
+        "model.layers.21.post_attention_layernorm": false,
+        "model.layers.22.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.22.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.22.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.22.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.22.self_attn.rope": false,
+        "model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.22.input_layernorm": false,
+        "model.layers.22.pre_feedforward_layernorm": false,
+        "model.layers.22.post_feedforward_layernorm": false,
+        "model.layers.22.post_attention_layernorm": false,
+        "model.layers.23.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.self_attn.rope": false,
+        "model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.input_layernorm": false,
+        "model.layers.23.pre_feedforward_layernorm": false,
+        "model.layers.23.post_feedforward_layernorm": false,
+        "model.layers.23.post_attention_layernorm": false,
+        "model.layers.24.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.self_attn.rope": false,
+        "model.layers.24.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.input_layernorm": false,
+        "model.layers.24.pre_feedforward_layernorm": false,
+        "model.layers.24.post_feedforward_layernorm": false,
+        "model.layers.24.post_attention_layernorm": false,
+        "model.layers.25.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.25.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.25.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.25.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.25.self_attn.rope": false,
+        "model.layers.25.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.25.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.25.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.25.input_layernorm": false,
+        "model.layers.25.pre_feedforward_layernorm": false,
+        "model.layers.25.post_feedforward_layernorm": false,
+        "model.layers.25.post_attention_layernorm": false,
+        "model.layers.26.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.self_attn.rope": false,
+        "model.layers.26.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.input_layernorm": false,
+        "model.layers.26.pre_feedforward_layernorm": false,
+        "model.layers.26.post_feedforward_layernorm": false,
+        "model.layers.26.post_attention_layernorm": false,
+        "model.layers.27.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.self_attn.rope": false,
+        "model.layers.27.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.input_layernorm": false,
+        "model.layers.27.pre_feedforward_layernorm": false,
+        "model.layers.27.post_feedforward_layernorm": false,
+        "model.layers.27.post_attention_layernorm": false,
+        "model.layers.28.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.28.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.28.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.28.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.28.self_attn.rope": false,
+        "model.layers.28.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.28.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.28.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.28.input_layernorm": false,
+        "model.layers.28.pre_feedforward_layernorm": false,
+        "model.layers.28.post_feedforward_layernorm": false,
+        "model.layers.28.post_attention_layernorm": false,
+        "model.layers.29.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.self_attn.rope": false,
+        "model.layers.29.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.input_layernorm": false,
+        "model.layers.29.pre_feedforward_layernorm": false,
+        "model.layers.29.post_feedforward_layernorm": false,
+        "model.layers.29.post_attention_layernorm": false,
+        "model.layers.30.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.self_attn.rope": false,
+        "model.layers.30.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.input_layernorm": false,
+        "model.layers.30.pre_feedforward_layernorm": false,
+        "model.layers.30.post_feedforward_layernorm": false,
+        "model.layers.30.post_attention_layernorm": false,
+        "model.layers.31.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.31.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.31.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.31.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.31.self_attn.rope": false,
+        "model.layers.31.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.31.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.31.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.31.input_layernorm": false,
+        "model.layers.31.pre_feedforward_layernorm": false,
+        "model.layers.31.post_feedforward_layernorm": false,
+        "model.layers.31.post_attention_layernorm": false,
+        "model.layers.32.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.self_attn.rope": false,
+        "model.layers.32.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.input_layernorm": false,
+        "model.layers.32.pre_feedforward_layernorm": false,
+        "model.layers.32.post_feedforward_layernorm": false,
+        "model.layers.32.post_attention_layernorm": false,
+        "model.layers.33.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.self_attn.rope": false,
+        "model.layers.33.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.input_layernorm": false,
+        "model.layers.33.pre_feedforward_layernorm": false,
+        "model.layers.33.post_feedforward_layernorm": false,
+        "model.layers.33.post_attention_layernorm": false,
+        "model.layers.34.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.34.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.34.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.34.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.34.self_attn.rope": false,
+        "model.layers.34.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.34.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.34.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.34.input_layernorm": false,
+        "model.layers.34.pre_feedforward_layernorm": false,
+        "model.layers.34.post_feedforward_layernorm": false,
+        "model.layers.34.post_attention_layernorm": false,
+        "model.layers.35.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.self_attn.rope": false,
+        "model.layers.35.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.input_layernorm": false,
+        "model.layers.35.pre_feedforward_layernorm": false,
+        "model.layers.35.post_feedforward_layernorm": false,
+        "model.layers.35.post_attention_layernorm": false,
+        "model.layers.36.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.36.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.36.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.36.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.36.self_attn.rope": false,
+        "model.layers.36.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.36.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.36.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.36.input_layernorm": false,
+        "model.layers.36.pre_feedforward_layernorm": false,
+        "model.layers.36.post_feedforward_layernorm": false,
+        "model.layers.36.post_attention_layernorm": false,
+        "model.layers.37.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.37.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.37.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.37.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.37.self_attn.rope": false,
+        "model.layers.37.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.37.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.37.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.37.input_layernorm": false,
+        "model.layers.37.pre_feedforward_layernorm": false,
+        "model.layers.37.post_feedforward_layernorm": false,
+        "model.layers.37.post_attention_layernorm": false,
+        "model.layers.38.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.38.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.38.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.38.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.38.self_attn.rope": false,
+        "model.layers.38.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.38.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.38.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.38.input_layernorm": false,
+        "model.layers.38.pre_feedforward_layernorm": false,
+        "model.layers.38.post_feedforward_layernorm": false,
+        "model.layers.38.post_attention_layernorm": false,
+        "model.layers.39.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.39.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.39.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.39.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.39.self_attn.rope": false,
+        "model.layers.39.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.39.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.39.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.39.input_layernorm": false,
+        "model.layers.39.pre_feedforward_layernorm": false,
+        "model.layers.39.post_feedforward_layernorm": false,
+        "model.layers.39.post_attention_layernorm": false,
+        "model.layers.40.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.40.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.40.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.40.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.40.self_attn.rope": false,
+        "model.layers.40.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.40.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.40.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.40.input_layernorm": false,
+        "model.layers.40.pre_feedforward_layernorm": false,
+        "model.layers.40.post_feedforward_layernorm": false,
+        "model.layers.40.post_attention_layernorm": false,
+        "model.layers.41.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.41.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.41.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.41.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.41.self_attn.rope": false,
+        "model.layers.41.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.41.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.41.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.41.input_layernorm": false,
+        "model.layers.41.pre_feedforward_layernorm": false,
+        "model.layers.41.post_feedforward_layernorm": false,
+        "model.layers.41.post_attention_layernorm": false,
+        "model.norm": false
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "model.embed_tokens": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.0.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.0.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.0.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.0.self_attn.rope": false,
+        "model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.0.input_layernorm": false,
+        "model.layers.0.pre_feedforward_layernorm": false,
+        "model.layers.0.post_feedforward_layernorm": false,
+        "model.layers.0.post_attention_layernorm": false,
+        "model.layers.1.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.1.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.1.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.1.self_attn.rope": false,
+        "model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.1.input_layernorm": false,
+        "model.layers.1.pre_feedforward_layernorm": false,
+        "model.layers.1.post_feedforward_layernorm": false,
+        "model.layers.1.post_attention_layernorm": false,
+        "model.layers.2.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.2.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.2.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.2.self_attn.rope": false,
+        "model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.2.input_layernorm": false,
+        "model.layers.2.pre_feedforward_layernorm": false,
+        "model.layers.2.post_feedforward_layernorm": false,
+        "model.layers.2.post_attention_layernorm": false,
+        "model.layers.3.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.3.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.3.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.3.self_attn.rope": false,
+        "model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.3.input_layernorm": false,
+        "model.layers.3.pre_feedforward_layernorm": false,
+        "model.layers.3.post_feedforward_layernorm": false,
+        "model.layers.3.post_attention_layernorm": false,
+        "model.layers.4.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.4.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.4.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.4.self_attn.rope": false,
+        "model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.4.input_layernorm": false,
+        "model.layers.4.pre_feedforward_layernorm": false,
+        "model.layers.4.post_feedforward_layernorm": false,
+        "model.layers.4.post_attention_layernorm": false,
+        "model.layers.5.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.self_attn.rope": false,
+        "model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.5.input_layernorm": false,
+        "model.layers.5.pre_feedforward_layernorm": false,
+        "model.layers.5.post_feedforward_layernorm": false,
+        "model.layers.5.post_attention_layernorm": false,
+        "model.layers.6.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.self_attn.rope": false,
+        "model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.6.input_layernorm": false,
+        "model.layers.6.pre_feedforward_layernorm": false,
+        "model.layers.6.post_feedforward_layernorm": false,
+        "model.layers.6.post_attention_layernorm": false,
+        "model.layers.7.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.7.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.7.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.7.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.7.self_attn.rope": false,
+        "model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.7.input_layernorm": false,
+        "model.layers.7.pre_feedforward_layernorm": false,
+        "model.layers.7.post_feedforward_layernorm": false,
+        "model.layers.7.post_attention_layernorm": false,
+        "model.layers.8.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.self_attn.rope": false,
+        "model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.8.input_layernorm": false,
+        "model.layers.8.pre_feedforward_layernorm": false,
+        "model.layers.8.post_feedforward_layernorm": false,
+        "model.layers.8.post_attention_layernorm": false,
+        "model.layers.9.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.self_attn.rope": false,
+        "model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.9.input_layernorm": false,
+        "model.layers.9.pre_feedforward_layernorm": false,
+        "model.layers.9.post_feedforward_layernorm": false,
+        "model.layers.9.post_attention_layernorm": false,
+        "model.layers.10.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.10.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.10.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.10.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.10.self_attn.rope": false,
+        "model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.10.input_layernorm": false,
+        "model.layers.10.pre_feedforward_layernorm": false,
+        "model.layers.10.post_feedforward_layernorm": false,
+        "model.layers.10.post_attention_layernorm": false,
+        "model.layers.11.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.self_attn.rope": false,
+        "model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.11.input_layernorm": false,
+        "model.layers.11.pre_feedforward_layernorm": false,
+        "model.layers.11.post_feedforward_layernorm": false,
+        "model.layers.11.post_attention_layernorm": false,
+        "model.layers.12.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.self_attn.rope": false,
+        "model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.12.input_layernorm": false,
+        "model.layers.12.pre_feedforward_layernorm": false,
+        "model.layers.12.post_feedforward_layernorm": false,
+        "model.layers.12.post_attention_layernorm": false,
+        "model.layers.13.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.13.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.13.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.13.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.13.self_attn.rope": false,
+        "model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.13.input_layernorm": false,
+        "model.layers.13.pre_feedforward_layernorm": false,
+        "model.layers.13.post_feedforward_layernorm": false,
+        "model.layers.13.post_attention_layernorm": false,
+        "model.layers.14.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.self_attn.rope": false,
+        "model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.14.input_layernorm": false,
+        "model.layers.14.pre_feedforward_layernorm": false,
+        "model.layers.14.post_feedforward_layernorm": false,
+        "model.layers.14.post_attention_layernorm": false,
+        "model.layers.15.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.self_attn.rope": false,
+        "model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.15.input_layernorm": false,
+        "model.layers.15.pre_feedforward_layernorm": false,
+        "model.layers.15.post_feedforward_layernorm": false,
+        "model.layers.15.post_attention_layernorm": false,
+        "model.layers.16.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.16.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.16.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.16.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.16.self_attn.rope": false,
+        "model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.16.input_layernorm": false,
+        "model.layers.16.pre_feedforward_layernorm": false,
+        "model.layers.16.post_feedforward_layernorm": false,
+        "model.layers.16.post_attention_layernorm": false,
+        "model.layers.17.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.self_attn.rope": false,
+        "model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.17.input_layernorm": false,
+        "model.layers.17.pre_feedforward_layernorm": false,
+        "model.layers.17.post_feedforward_layernorm": false,
+        "model.layers.17.post_attention_layernorm": false,
+        "model.layers.18.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.self_attn.rope": false,
+        "model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.18.input_layernorm": false,
+        "model.layers.18.pre_feedforward_layernorm": false,
+        "model.layers.18.post_feedforward_layernorm": false,
+        "model.layers.18.post_attention_layernorm": false,
+        "model.layers.19.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.19.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.19.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.19.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.19.self_attn.rope": false,
+        "model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.19.input_layernorm": false,
+        "model.layers.19.pre_feedforward_layernorm": false,
+        "model.layers.19.post_feedforward_layernorm": false,
+        "model.layers.19.post_attention_layernorm": false,
+        "model.layers.20.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.self_attn.rope": false,
+        "model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.20.input_layernorm": false,
+        "model.layers.20.pre_feedforward_layernorm": false,
+        "model.layers.20.post_feedforward_layernorm": false,
+        "model.layers.20.post_attention_layernorm": false,
+        "model.layers.21.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.self_attn.rope": false,
+        "model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.21.input_layernorm": false,
+        "model.layers.21.pre_feedforward_layernorm": false,
+        "model.layers.21.post_feedforward_layernorm": false,
+        "model.layers.21.post_attention_layernorm": false,
+        "model.layers.22.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.22.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.22.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.22.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.22.self_attn.rope": false,
+        "model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.22.input_layernorm": false,
+        "model.layers.22.pre_feedforward_layernorm": false,
+        "model.layers.22.post_feedforward_layernorm": false,
+        "model.layers.22.post_attention_layernorm": false,
+        "model.layers.23.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.self_attn.rope": false,
+        "model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.23.input_layernorm": false,
+        "model.layers.23.pre_feedforward_layernorm": false,
+        "model.layers.23.post_feedforward_layernorm": false,
+        "model.layers.23.post_attention_layernorm": false,
+        "model.layers.24.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.self_attn.rope": false,
+        "model.layers.24.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.24.input_layernorm": false,
+        "model.layers.24.pre_feedforward_layernorm": false,
+        "model.layers.24.post_feedforward_layernorm": false,
+        "model.layers.24.post_attention_layernorm": false,
+        "model.layers.25.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.25.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.25.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.25.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.25.self_attn.rope": false,
+        "model.layers.25.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.25.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.25.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.25.input_layernorm": false,
+        "model.layers.25.pre_feedforward_layernorm": false,
+        "model.layers.25.post_feedforward_layernorm": false,
+        "model.layers.25.post_attention_layernorm": false,
+        "model.layers.26.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.self_attn.rope": false,
+        "model.layers.26.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.26.input_layernorm": false,
+        "model.layers.26.pre_feedforward_layernorm": false,
+        "model.layers.26.post_feedforward_layernorm": false,
+        "model.layers.26.post_attention_layernorm": false,
+        "model.layers.27.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.self_attn.rope": false,
+        "model.layers.27.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.27.input_layernorm": false,
+        "model.layers.27.pre_feedforward_layernorm": false,
+        "model.layers.27.post_feedforward_layernorm": false,
+        "model.layers.27.post_attention_layernorm": false,
+        "model.layers.28.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.28.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.28.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.28.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.28.self_attn.rope": false,
+        "model.layers.28.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.28.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.28.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.28.input_layernorm": false,
+        "model.layers.28.pre_feedforward_layernorm": false,
+        "model.layers.28.post_feedforward_layernorm": false,
+        "model.layers.28.post_attention_layernorm": false,
+        "model.layers.29.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.self_attn.rope": false,
+        "model.layers.29.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.29.input_layernorm": false,
+        "model.layers.29.pre_feedforward_layernorm": false,
+        "model.layers.29.post_feedforward_layernorm": false,
+        "model.layers.29.post_attention_layernorm": false,
+        "model.layers.30.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.self_attn.rope": false,
+        "model.layers.30.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.30.input_layernorm": false,
+        "model.layers.30.pre_feedforward_layernorm": false,
+        "model.layers.30.post_feedforward_layernorm": false,
+        "model.layers.30.post_attention_layernorm": false,
+        "model.layers.31.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.31.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.31.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.31.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.31.self_attn.rope": false,
+        "model.layers.31.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.31.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.31.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.31.input_layernorm": false,
+        "model.layers.31.pre_feedforward_layernorm": false,
+        "model.layers.31.post_feedforward_layernorm": false,
+        "model.layers.31.post_attention_layernorm": false,
+        "model.layers.32.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.self_attn.rope": false,
+        "model.layers.32.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.32.input_layernorm": false,
+        "model.layers.32.pre_feedforward_layernorm": false,
+        "model.layers.32.post_feedforward_layernorm": false,
+        "model.layers.32.post_attention_layernorm": false,
+        "model.layers.33.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.self_attn.rope": false,
+        "model.layers.33.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.33.input_layernorm": false,
+        "model.layers.33.pre_feedforward_layernorm": false,
+        "model.layers.33.post_feedforward_layernorm": false,
+        "model.layers.33.post_attention_layernorm": false,
+        "model.layers.34.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.34.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.34.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.34.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.34.self_attn.rope": false,
+        "model.layers.34.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.34.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.34.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.34.input_layernorm": false,
+        "model.layers.34.pre_feedforward_layernorm": false,
+        "model.layers.34.post_feedforward_layernorm": false,
+        "model.layers.34.post_attention_layernorm": false,
+        "model.layers.35.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.self_attn.rope": false,
+        "model.layers.35.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.35.input_layernorm": false,
+        "model.layers.35.pre_feedforward_layernorm": false,
+        "model.layers.35.post_feedforward_layernorm": false,
+        "model.layers.35.post_attention_layernorm": false,
+        "model.layers.36.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.36.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.36.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.36.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.36.self_attn.rope": false,
+        "model.layers.36.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.36.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.36.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.36.input_layernorm": false,
+        "model.layers.36.pre_feedforward_layernorm": false,
+        "model.layers.36.post_feedforward_layernorm": false,
+        "model.layers.36.post_attention_layernorm": false,
+        "model.layers.37.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.37.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.37.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.37.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.37.self_attn.rope": false,
+        "model.layers.37.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.37.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.37.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.37.input_layernorm": false,
+        "model.layers.37.pre_feedforward_layernorm": false,
+        "model.layers.37.post_feedforward_layernorm": false,
+        "model.layers.37.post_attention_layernorm": false,
+        "model.layers.38.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.38.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.38.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.38.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.38.self_attn.rope": false,
+        "model.layers.38.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.38.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.38.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.38.input_layernorm": false,
+        "model.layers.38.pre_feedforward_layernorm": false,
+        "model.layers.38.post_feedforward_layernorm": false,
+        "model.layers.38.post_attention_layernorm": false,
+        "model.layers.39.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.39.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.39.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.39.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.39.self_attn.rope": false,
+        "model.layers.39.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.39.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.39.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.39.input_layernorm": false,
+        "model.layers.39.pre_feedforward_layernorm": false,
+        "model.layers.39.post_feedforward_layernorm": false,
+        "model.layers.39.post_attention_layernorm": false,
+        "model.layers.40.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.40.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.40.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.40.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.40.self_attn.rope": false,
+        "model.layers.40.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.40.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.40.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.40.input_layernorm": false,
+        "model.layers.40.pre_feedforward_layernorm": false,
+        "model.layers.40.post_feedforward_layernorm": false,
+        "model.layers.40.post_attention_layernorm": false,
+        "model.layers.41.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.41.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.41.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.41.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.41.self_attn.rope": false,
+        "model.layers.41.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.41.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.layers.41.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "model.layers.41.input_layernorm": false,
+        "model.layers.41.pre_feedforward_layernorm": false,
+        "model.layers.41.post_feedforward_layernorm": false,
+        "model.layers.41.post_attention_layernorm": false,
+        "model.norm": false
+    },
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 10000.0,
+    "sliding_window": 4096,
+    "sliding_window_size": 4096,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.42.4",
+    "use_cache": true,
+    "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [1, 107],
+  "pad_token_id": 0,
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71dd3fa49c7f2cc5ad02befdf82ec96a0d0793b6375fd52804eb8f88895207d5
+size 4506735751

model.safetensors.index.json

@@ -0,0 +1,1062 @@
+{
+    "metadata": {
+        "total_size": 4506614784,
+        "total_parameters": 9241705984
+    },
+    "weight_map": {
+        "model.embed_tokens.biases": "model.safetensors",
+        "model.embed_tokens.scales": "model.safetensors",
+        "model.embed_tokens.weight": "model.safetensors",
+        "model.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.0.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.0.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.1.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.1.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.10.input_layernorm.weight": "model.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.10.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.10.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.11.input_layernorm.weight": "model.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.11.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.11.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.12.input_layernorm.weight": "model.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.12.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.12.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.13.input_layernorm.weight": "model.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.13.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.13.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.14.input_layernorm.weight": "model.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.14.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.14.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.15.input_layernorm.weight": "model.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.15.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.15.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.16.input_layernorm.weight": "model.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.16.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.16.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.17.input_layernorm.weight": "model.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.17.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.17.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.18.input_layernorm.weight": "model.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.18.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.18.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.19.input_layernorm.weight": "model.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.19.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.19.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.2.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.2.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.20.input_layernorm.weight": "model.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.20.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.20.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.21.input_layernorm.weight": "model.safetensors",
+        "model.layers.21.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.21.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.21.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.22.input_layernorm.weight": "model.safetensors",
+        "model.layers.22.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.22.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.22.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.23.input_layernorm.weight": "model.safetensors",
+        "model.layers.23.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.23.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.23.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.24.input_layernorm.weight": "model.safetensors",
+        "model.layers.24.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.24.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.24.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.24.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.24.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.24.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.24.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.24.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.25.input_layernorm.weight": "model.safetensors",
+        "model.layers.25.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.25.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.25.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.25.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.25.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.25.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.25.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.25.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.26.input_layernorm.weight": "model.safetensors",
+        "model.layers.26.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.26.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.26.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.26.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.26.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.26.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.26.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.26.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.27.input_layernorm.weight": "model.safetensors",
+        "model.layers.27.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.27.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.27.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.27.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.27.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.27.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.27.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.27.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.27.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.28.input_layernorm.weight": "model.safetensors",
+        "model.layers.28.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.28.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.28.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.28.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.28.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.28.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.28.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.28.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.28.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.28.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.28.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.28.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.28.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.29.input_layernorm.weight": "model.safetensors",
+        "model.layers.29.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.29.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.29.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.29.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.29.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.29.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.29.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.29.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.29.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.3.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.3.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.30.input_layernorm.weight": "model.safetensors",
+        "model.layers.30.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.30.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.30.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.30.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.30.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.30.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.30.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.30.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.30.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.31.input_layernorm.weight": "model.safetensors",
+        "model.layers.31.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.31.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.31.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.31.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.31.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.31.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.31.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.31.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.31.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.31.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.31.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.31.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.31.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.32.input_layernorm.weight": "model.safetensors",
+        "model.layers.32.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.32.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.32.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.32.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.32.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.32.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.32.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.32.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.32.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.32.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.32.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.32.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.32.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.32.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.32.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.32.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.33.input_layernorm.weight": "model.safetensors",
+        "model.layers.33.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.33.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.33.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.33.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.33.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.33.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.33.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.33.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.33.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.33.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.33.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.33.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.33.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.33.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.33.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.33.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.34.input_layernorm.weight": "model.safetensors",
+        "model.layers.34.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.34.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.34.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.34.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.34.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.34.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.34.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.34.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.34.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.34.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.34.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.34.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.34.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.34.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.34.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.34.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.35.input_layernorm.weight": "model.safetensors",
+        "model.layers.35.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.35.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.35.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.35.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.35.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.35.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.35.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.35.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.35.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.35.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.35.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.35.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.35.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.35.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.35.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.35.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.36.input_layernorm.weight": "model.safetensors",
+        "model.layers.36.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.36.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.36.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.36.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.36.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.36.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.36.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.36.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.36.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.36.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.36.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.36.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.36.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.36.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.36.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.36.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.37.input_layernorm.weight": "model.safetensors",
+        "model.layers.37.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.37.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.37.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.37.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.37.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.37.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.37.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.37.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.37.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.37.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.37.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.37.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.37.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.37.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.37.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.37.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.38.input_layernorm.weight": "model.safetensors",
+        "model.layers.38.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.38.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.38.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.38.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.38.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.38.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.38.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.38.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.38.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.38.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.38.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.38.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.38.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.38.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.38.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.38.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.39.input_layernorm.weight": "model.safetensors",
+        "model.layers.39.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.39.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.39.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.39.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.39.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.39.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.39.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.39.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.39.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.39.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.39.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.39.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.39.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.39.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.39.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.39.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.4.input_layernorm.weight": "model.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.4.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.4.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.40.input_layernorm.weight": "model.safetensors",
+        "model.layers.40.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.40.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.40.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.40.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.40.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.40.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.40.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.40.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.40.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.40.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.40.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.40.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.40.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.40.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.40.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.40.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.41.input_layernorm.weight": "model.safetensors",
+        "model.layers.41.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.41.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.41.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.41.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.41.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.41.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.41.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.41.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.41.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.41.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.41.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.41.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.41.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.41.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.41.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.41.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.5.input_layernorm.weight": "model.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.5.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.5.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.6.input_layernorm.weight": "model.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.6.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.6.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.7.input_layernorm.weight": "model.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.7.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.7.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.8.input_layernorm.weight": "model.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.8.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.8.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.9.input_layernorm.weight": "model.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.9.post_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.9.pre_feedforward_layernorm.weight": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "model.norm.weight": "model.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,1758 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] | trim + '\n\n' %}{% set messages = messages[1:] %}{% else %}{% set system_message = '' %}{% endif %}{% for message in messages %}{% if loop.index0 == 0 %}{% set content = system_message + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + content | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}