Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|endoftext|>": 151643,
+  "<|extra_0|>": 151646,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,93 @@
+{
+  "_name_or_path": "./checkpoints/llavaqwen1.5-1.8b-ft-mergedlora",
+  "architectures": [
+    "MoELLaVAQwen1_5ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "pad",
+  "image_projector_type": "mlp2x_gelu",
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "lora": {},
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "mm_hidden_size": 768,
+  "mm_image_tower": "google/siglip-base-patch16-256-multilingual",
+  "mm_projector_lr": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_video_tower": null,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "model_type": "moe_llava_qwen1_5",
+  "moe": {
+    "capacity_factor": 1.5,
+    "ep_size": 1,
+    "eval_capacity_factor": 2.0,
+    "min_capacity": 0,
+    "moe_enable": true,
+    "moe_layers_idx": [
+      0,
+      2,
+      4,
+      6,
+      8,
+      10,
+      12,
+      14,
+      16,
+      18,
+      20,
+      22
+    ],
+    "moe_mode": "sparse",
+    "num_experts": [
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4
+    ],
+    "router_aux_loss_coef": 0.01,
+    "top_k_experts": 2,
+    "train_modules": [
+      "mlp.gate_proj",
+      "mlp.up_proj",
+      "mlp.down_proj",
+      "wg"
+    ],
+    "use_residual": false
+  },
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "use_sliding_window": false,
+  "video_global_proj": false,
+  "video_projector_type": "linear",
+  "video_spatial_proj": false,
+  "video_temproal_proj": false,
+  "vocab_size": 151646
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.37.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:980a830b59160d9afd549825ae05b088f6d0537baf860bd074e89090cf430504
+size 4995418608

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c6b4f463f8c8479cebdbb276aa0afa9d092fe6fc04a2feb6e2f21f13ab8aa3
+size 1308341240

model.safetensors.index.json

@@ -0,0 +1,630 @@
+{
+  "metadata": {
+    "total_size": 6303674880
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.embeddings.patch_embedding.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.head.attention.in_proj_bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.head.attention.in_proj_weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.head.attention.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.head.attention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.head.layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.head.layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.head.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.head.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.head.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.head.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.head.probe": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.image_tower.image_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.deepspeed_moe.gate.wg.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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.deepspeed_moe.gate.wg.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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.deepspeed_moe.gate.wg.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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.deepspeed_moe.gate.wg.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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.deepspeed_moe.gate.wg.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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.deepspeed_moe.gate.wg.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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.deepspeed_moe.gate.wg.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.bias": "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.bias": "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.bias": "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.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.deepspeed_moe.gate.wg.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.bias": "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.bias": "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.bias": "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-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "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-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "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.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.deepspeed_moe.gate.wg.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-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.bias": "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.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.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.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.deepspeed_moe.gate.wg.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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.deepspeed_moe.gate.wg.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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.deepspeed_moe.gate.wg.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.bias": "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.bias": "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.bias": "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-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.image_spatial_proj.0.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.image_spatial_proj.0.weight": "model-00002-of-00002.safetensors",
+    "model.mm_projector.image_spatial_proj.2.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.image_spatial_proj.2.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|extra_0|>",
+  "unk_token": {
+    "content": "<|extra_0|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "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": "<|extra_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|extra_0|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": "<|extra_0|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336a685fc0e4208e38689069aad9bf542b4c185853f82cb2ba55c83866b567be
+size 5883