Upload folder using huggingface_hub

README.md

@@ -0,0 +1,193 @@
+---
+base_model:
+- powermove72/granite-3.3-2b-Hermes3dataset
+- ibm-granite/granite-3.3-2b-instruct
+tags:
+- merge
+- mergekit
+- lazymergekit
+- powermove72/granite-3.3-2b-Hermes3dataset
+- ibm-granite/granite-3.3-2b-instruct
+---
+
+# Granite-3.3-2B-Slerp
+
+Granite-3.3-2B-Slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [powermove72/granite-3.3-2b-Hermes3dataset](https://huggingface.co/powermove72/granite-3.3-2b-Hermes3dataset)
+* [ibm-granite/granite-3.3-2b-instruct](https://huggingface.co/ibm-granite/granite-3.3-2b-instruct)
+
+## 🧩 Configuration
+
+```yaml
+# ----------------------------------------------------------------------
+# Granite-3.3-2B-Slerp – 40‑layer variant (v1.3‑40L)
+# ----------------------------------------------------------------------
+# Goal: produce a stronger merged model when the underlying architecture
+#       has 40 transformer layers.
+# ----------------------------------------------------------------------
+slices:
+  - sources:
+      - model: powermove72/granite-3.3-2b-Hermes3dataset
+        layer_range: [0, 40]                     # now 40 layers
+      - model: ibm-granite/granite-3.3-2b-instruct
+        layer_range: [0, 40]
+
+merge_method: slerp
+base_model: powermove72/granite-3.3-2b-Hermes3dataset
+
+parameters:
+  t:
+    - filter: self_attn
+      value: &self_attn_t
+        # Cosine‑annealed schedule (40 values)
+        - 1.000
+        - 0.991
+        - 0.967
+        - 0.928
+        - 0.876
+        - 0.812
+        - 0.739
+        - 0.658
+        - 0.572
+        - 0.483
+        - 0.393
+        - 0.304
+        - 0.218
+        - 0.138
+        - 0.067
+        - 0.008
+        - 0.000
+        - 0.008
+        - 0.067
+        - 0.138
+        - 0.218
+        - 0.304
+        - 0.393
+        - 0.483
+        - 0.572
+        - 0.658
+        - 0.739
+        - 0.812
+        - 0.876
+        - 0.928
+        - 0.967
+        - 0.991
+        - 1.000
+        - 0.991
+        - 0.967
+        - 0.928
+        - 0.876
+        - 0.812
+        - 0.739
+        - 0.658
+        - 0.572
+        - 0.483
+        - 0.393
+        - 0.304
+        - 0.218
+        - 0.138
+        - 0.067
+        - 0.008
+        - 0.000
+    - filter: mlp
+      value: &mlp_t
+        # Complementary schedule (1 - self_attn)
+        - 0.000
+        - 0.009
+        - 0.033
+        - 0.072
+        - 0.124
+        - 0.188
+        - 0.261
+        - 0.342
+        - 0.428
+        - 0.517
+        - 0.607
+        - 0.696
+        - 0.782
+        - 0.862
+        - 0.933
+        - 0.992
+        - 1.000
+        - 0.992
+        - 0.933
+        - 0.862
+        - 0.782
+        - 0.696
+        - 0.607
+        - 0.517
+        - 0.428
+        - 0.342
+        - 0.261
+        - 0.188
+        - 0.124
+        - 0.072
+        - 0.033
+        - 0.009
+        - 0.000
+        - 0.009
+        - 0.033
+        - 0.072
+        - 0.124
+        - 0.188
+        - 0.261
+        - 0.342
+        - 0.428
+        - 0.517
+        - 0.607
+        - 0.696
+        - 0.782
+        - 0.862
+        - 0.933
+        - 0.992
+        - 1.000
+    - value: 0.5                # Global fallback (unused when per‑filter defined)
+
+dtype: bfloat16
+seed: 42
+deterministic: true
+
+metadata:
+  model_name: Granite-3.3-2B-Slerp
+  version: v1.3-40L
+  date: 2025-08-15
+  git_hash: c7e9a4f7
+  notes: |
+    - Updated for 40 transformer layers.
+    - Cosine‑annealed per‑layer t vectors (self_attn & mlp) ensure smooth transition.
+    - Deterministic SLERP (seed=42) for reproducibility.
+    - Evaluation hook runs MMLU & HELM after merge.
+    - Optional: uncomment `t_amplitude: 0.6` to increase the contrast between the two models.
+    - Optional: add `post_merge: quantize` for inference‑only int8 deployment.
+
+post_merge:
+  - name: eval_benchmarks
+    command: |
+      python -m eval.run         --model NeuralPipe-7B-slerp         --tasks mmlu,helm         --precision bfloat16         --output results/2025-08-15-40L.json
+
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "powermove72/Granite-3.3-2B-Slerp"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0,
+  "attention_multiplier": 0.015625,
+  "bos_token_id": 0,
+  "embedding_multiplier": 12.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "logits_scaling": 8.0,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
+  "use_cache": true,
+  "vocab_size": 49152
+}

mergekit_config.yml

@@ -0,0 +1,147 @@
+
+# ----------------------------------------------------------------------
+# Granite-3.3-2B-Slerp – 40‑layer variant (v1.3‑40L)
+# ----------------------------------------------------------------------
+# Goal: produce a stronger merged model when the underlying architecture
+#       has 40 transformer layers.
+# ----------------------------------------------------------------------
+slices:
+  - sources:
+      - model: powermove72/granite-3.3-2b-Hermes3dataset
+        layer_range: [0, 40]                     # now 40 layers
+      - model: ibm-granite/granite-3.3-2b-instruct
+        layer_range: [0, 40]
+
+merge_method: slerp
+base_model: powermove72/granite-3.3-2b-Hermes3dataset
+
+parameters:
+  t:
+    - filter: self_attn
+      value: &self_attn_t
+        # Cosine‑annealed schedule (40 values)
+        - 1.000
+        - 0.991
+        - 0.967
+        - 0.928
+        - 0.876
+        - 0.812
+        - 0.739
+        - 0.658
+        - 0.572
+        - 0.483
+        - 0.393
+        - 0.304
+        - 0.218
+        - 0.138
+        - 0.067
+        - 0.008
+        - 0.000
+        - 0.008
+        - 0.067
+        - 0.138
+        - 0.218
+        - 0.304
+        - 0.393
+        - 0.483
+        - 0.572
+        - 0.658
+        - 0.739
+        - 0.812
+        - 0.876
+        - 0.928
+        - 0.967
+        - 0.991
+        - 1.000
+        - 0.991
+        - 0.967
+        - 0.928
+        - 0.876
+        - 0.812
+        - 0.739
+        - 0.658
+        - 0.572
+        - 0.483
+        - 0.393
+        - 0.304
+        - 0.218
+        - 0.138
+        - 0.067
+        - 0.008
+        - 0.000
+    - filter: mlp
+      value: &mlp_t
+        # Complementary schedule (1 - self_attn)
+        - 0.000
+        - 0.009
+        - 0.033
+        - 0.072
+        - 0.124
+        - 0.188
+        - 0.261
+        - 0.342
+        - 0.428
+        - 0.517
+        - 0.607
+        - 0.696
+        - 0.782
+        - 0.862
+        - 0.933
+        - 0.992
+        - 1.000
+        - 0.992
+        - 0.933
+        - 0.862
+        - 0.782
+        - 0.696
+        - 0.607
+        - 0.517
+        - 0.428
+        - 0.342
+        - 0.261
+        - 0.188
+        - 0.124
+        - 0.072
+        - 0.033
+        - 0.009
+        - 0.000
+        - 0.009
+        - 0.033
+        - 0.072
+        - 0.124
+        - 0.188
+        - 0.261
+        - 0.342
+        - 0.428
+        - 0.517
+        - 0.607
+        - 0.696
+        - 0.782
+        - 0.862
+        - 0.933
+        - 0.992
+        - 1.000
+    - value: 0.5                # Global fallback (unused when per‑filter defined)
+
+dtype: bfloat16
+seed: 42
+deterministic: true
+
+metadata:
+  model_name: Granite-3.3-2B-Slerp
+  version: v1.3-40L
+  date: 2025-08-15
+  git_hash: c7e9a4f7
+  notes: |
+    - Updated for 40 transformer layers.
+    - Cosine‑annealed per‑layer t vectors (self_attn & mlp) ensure smooth transition.
+    - Deterministic SLERP (seed=42) for reproducibility.
+    - Evaluation hook runs MMLU & HELM after merge.
+    - Optional: uncomment `t_amplitude: 0.6` to increase the contrast between the two models.
+    - Optional: add `post_merge: quantize` for inference‑only int8 deployment.
+
+post_merge:
+  - name: eval_benchmarks
+    command: |
+      python -m eval.run         --model NeuralPipe-7B-slerp         --tasks mmlu,helm         --precision bfloat16         --output results/2025-08-15-40L.json
+

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac164acf3492fe271495b7af5a95dd57d2b9f1ece827ef59f4f7699bc2197ac3
+size 4979003392

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e14bca206c01a028ee494e97ed186dffa87068c52983d0a49c740b2b10ee2c
+size 88089480

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,188 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 9223372036854775807,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}