Delete models

models/config.json

@@ -1,87 +0,0 @@
-{
-  "architectures": [
-    "MiMoForCausalLM"
-  ],
-  "attention_bias": true,
-  "attention_dropout": 0.0,
-  "auto_map": {
-  "AutoConfig": "configuration_mimo.MiMoConfig",
-  "AutoModel": "modeling_mimo.MiMoModel",
-  "AutoModelForCausalLM": "modeling_mimo.MiMoForCausalLM"
-  },
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "layer_types": [
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention"
-  ],
-  "max_position_embeddings": 32768,
-  "max_window_layers": 36,
-  "model_type": "mimo",
-  "mtp_loss_step_weights": [
-    0.51,
-    0.31,
-    0.18
-  ],
-  "mtp_loss_weight": 1.0,
-  "ntp_loss_weight": 0.0,
-  "num_attention_heads": 32,
-  "num_hidden_layers": 36,
-  "num_key_value_heads": 8,
-  "num_nextn_predict_layers": 1,
-  "num_speculative_steps": 3,
-  "pad_token_id": 151643,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 640000,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "tokenizer_class": [
-    "Qwen2Tokenizer"
-  ],
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.54.0",
-  "use_cache": false,
-  "use_mrope": false,
-  "use_sliding_window": false,
-  "vocab_size": 151680
-}

models/configuration_mimo.py

@@ -1,16 +0,0 @@
-from transformers.models.qwen2.configuration_qwen2 import Qwen2Config
-
-class MiMoConfig(Qwen2Config):
-    model_type = "mimo"
-
-    def __init__(
-        self,
-        *args,
-        num_nextn_predict_layers=0,
-        **kwargs
-    ):
-        self.num_nextn_predict_layers = num_nextn_predict_layers
-        super().__init__(
-            *args,
-            **kwargs,
-        )

models/generation_config.json

@@ -1,9 +0,0 @@
-{
-  "bos_token_id": 151643,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "max_new_tokens": 2048,
-  "transformers_version": "4.54.0"
-}

models/model-00001-of-00004.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6a313e572a8c845b1a7aeec0b2c40bf5895b69739ed71b32c408b3c992361858
-size 4961126848

models/model-00002-of-00004.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cbde26739354e8ebbf63a4d4a8a97dbc331144c14f0b29755b6102adddb17954
-size 4962282376

models/model-00003-of-00004.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6718f5323956d46439fdd904fb79d877f02cf692c58e630d430f98943931c13d
-size 4500899032

models/model-00004-of-00004.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cf1824de08c6a27c0d26d567847679b0f374aee8d565e011856b7e604572f816
-size 1242562688

models/model.safetensors.index.json

@@ -1,459 +0,0 @@
-{
-  "metadata": {
-    "total_parameters": 7833409536,
-    "total_size": 15666819072
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00004-of-00004.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.mtp_layers.0.final_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.hidden_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.input_proj.weight": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.mtp_layers.0.token_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.norm.weight": "model-00003-of-00004.safetensors"
-  }
-}

models/modeling_mimo.py

@@ -1,75 +0,0 @@
-from typing import Optional, Tuple
-
-import torch
-from torch import nn
-from transformers.cache_utils import Cache
-from transformers.models.qwen2.modeling_qwen2 import (Qwen2Attention,
-                                                      Qwen2ForCausalLM,
-                                                      Qwen2MLP, Qwen2Model,
-                                                      Qwen2RMSNorm)
-
-from .configuration_mimo import MiMoConfig
-
-
-class MiMoMTPLayers(nn.Module):
-    def __init__(self, config):
-        super().__init__()
-        self.input_layernorm = Qwen2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
-        self.post_attention_layernorm = Qwen2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
-        self.token_layernorm = Qwen2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
-        self.hidden_layernorm = Qwen2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
-        self.input_proj = nn.Linear(config.hidden_size * 2, config.hidden_size, bias=False)
-        self.final_layernorm = Qwen2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
-        self.self_attn = Qwen2Attention(config, layer_idx=0)
-        self.mlp = Qwen2MLP(config)
-
-    def forward(self, input_embeds,
-                    hidden_states,
-                    attention_mask,
-                    position_ids,
-                    past_key_values: Optional[Cache]=None,
-                    output_attentions: Optional[bool]=False,
-                    use_cache: Optional[bool]=False,
-                    position_embedding: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
-                    cache_position=None,
-                    **kwargs):
-        input_embeds = self.token_layernorm(input_embeds)
-        previous_hidden_states = self.hidden_layernorm(hidden_states)
-        hidden_states = self.input_proj(torch.cat([previous_hidden_states, input_embeds], dim=-1))
-        residual = hidden_states
-        hidden_states = self.input_layernorm(hidden_states)
-        hidden_states, _ = self.self_attn(hidden_states,
-                                       attention_mask=attention_mask,
-                                       position_ids=position_ids,
-                                       past_key_values=past_key_values,
-                                       output_attentions=output_attentions,
-                                       use_cache=use_cache,
-                                       cache_position=cache_position,
-                                       position_embedding=position_embedding,
-                                       **kwargs)
-        hidden_states = residual + hidden_states
-        residual = hidden_states
-        hidden_states = self.post_attention_layernorm(hidden_states)
-        hidden_states = self.mlp(hidden_states)
-        hidden_states = residual + hidden_states
-        hidden_states = self.final_layernorm(hidden_states)
-        return hidden_states
-
-
-class MiMoModel(Qwen2Model):
-    config_class = MiMoConfig
-
-    def __init__(self, config: MiMoConfig):
-        super().__init__(config)
-        self.mtp_layers = nn.ModuleList([MiMoMTPLayers(config) for _ in range(config.num_nextn_predict_layers)])
-
-
-class MiMoForCausalLM(Qwen2ForCausalLM):
-    config_class = MiMoConfig
-    def __init__(self, config: MiMoConfig):
-        super(Qwen2ForCausalLM, self).__init__(config)
-        self.model = MiMoModel(config)
-        self.vocab_size = config.vocab_size
-        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
-
-        self.post_init()

models/special_tokens_map.json

@@ -1,31 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

models/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896

models/tokenizer_config.json

@@ -1,207 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}