Upload folder using huggingface_hub

README.md

@@ -0,0 +1,22 @@
+---
+license: other
+license_name: deepseek
+license_link: https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- mlx
+---
+
+# mlx-community/deepseek-vl2-bf16
+This model was converted to MLX format from [`prince-canuma/deepseek-vl2`]() using mlx-vlm version **0.1.5**.
+Refer to the [original model card](https://huggingface.co/prince-canuma/deepseek-vl2) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model mlx-community/deepseek-vl2-bf16 --max-tokens 100 --temp 0.0
+```

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}<|User|>:{% elif message['role'] == 'assistant' %}<|Assistant|>{% endif %} {{message['content']}}\n\n{% endfor %}{% if add_generation_prompt %}<|Assistant|>:{% endif %}"
+}

config.json

@@ -0,0 +1,145 @@
+{
+    "candidate_resolutions": [
+        [
+            384,
+            384
+        ],
+        [
+            384,
+            768
+        ],
+        [
+            768,
+            384
+        ],
+        [
+            384,
+            1152
+        ],
+        [
+            1152,
+            384
+        ],
+        [
+            384,
+            1536
+        ],
+        [
+            1536,
+            384
+        ],
+        [
+            768,
+            768
+        ],
+        [
+            384,
+            1920
+        ],
+        [
+            1920,
+            384
+        ],
+        [
+            384,
+            2304
+        ],
+        [
+            2304,
+            384
+        ],
+        [
+            768,
+            1152
+        ],
+        [
+            1152,
+            768
+        ],
+        [
+            384,
+            2688
+        ],
+        [
+            2688,
+            384
+        ],
+        [
+            384,
+            3072
+        ],
+        [
+            3072,
+            384
+        ],
+        [
+            768,
+            1536
+        ],
+        [
+            1536,
+            768
+        ],
+        [
+            384,
+            3456
+        ],
+        [
+            3456,
+            384
+        ],
+        [
+            1152,
+            1152
+        ]
+    ],
+    "global_view_pos": "head",
+    "language_config": {
+        "architectures": [
+            "DeepseekV2ForCausalLM"
+        ],
+        "auto_map": {
+            "AutoConfig": "configuration_deepseek.DeepseekV2Config",
+            "AutoModel": "modeling_deepseek.DeepseekV2Model",
+            "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
+        },
+        "bos_token_id": 0,
+        "eos_token_id": 1,
+        "first_k_dense_replace": 1,
+        "hidden_size": 2560,
+        "intermediate_size": 12288,
+        "lm_head": false,
+        "max_position_embeddings": 4096,
+        "model_type": "deepseek_v2",
+        "moe_intermediate_size": 1536,
+        "n_group": 1,
+        "n_routed_experts": 72,
+        "n_shared_experts": 2,
+        "norm_topk_prob": true,
+        "num_experts_per_tok": 6,
+        "q_lora_rank": null,
+        "rm_head": false,
+        "routed_scaling_factor": 2.0,
+        "scoring_func": "sigmoid",
+        "topk_group": 1,
+        "topk_method": "noaux_tc",
+        "torch_dtype": "bfloat16",
+        "vocab_size": 129280
+    },
+    "model_type": "deepseek_vl_v2",
+    "projector_config": {
+        "model_type": "mlp_projector",
+        "n_embed": 2560
+    },
+    "tile_tag": "2D",
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.38.2",
+    "vision_config": {
+        "layers": 27,
+        "mlp_ratio": 3.7362,
+        "model_name": "siglip_so400m_patch14_384",
+        "model_type": "vision",
+        "patch_size": 14,
+        "width": 1152
+    }
+}

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9ece9eff18551e907e14ff52d208d98acdcbdb1fc2b2d3b0b90d87d1239d9f4
+size 5359515338

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb4575aae88888675f462c59a2b6091654194c16d17d71209f8fb9599ab0f9b6
+size 4847754000

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6cc8d93a73f12eb16540acc51d6c00323c1da5e30ee9bf23d47f6848d4ef733
+size 4863851812

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa2ea3e6556161f14a41363e0dcbdf3638541c6ee9986abf4fd63ea3eb595087
+size 4863851820

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99eb6413deb2ec40a0061dcef3f20134012656ea51528875d2125b1359f9ed38
+size 5366314788

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a348e5fe075781a1b068bbcac9a04fa7850f514aae48887f955cd4b06b641d9f
+size 4816285978

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae69e52c5877673394684a01ad4cbfa511b5999df5c8ae706a0a9c32d7d35dc0
+size 4863851868

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e67affef6a3a1a73fd70899a4f2e246ed7b2f580aa27004c8744be6b852e01
+size 4863851850

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc18f9fb0a8407ec4fc9aaaa2cee15fcf21044cc141ff2ae65dd0494de2774ec
+size 5366314796

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135c91636d28ba62d219ed3ca0ce74a4bf79660a7922e03157be7f7e1717eab5
+size 4816285984

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d30162602337b783dec3ff9d52fe8c85ac103832c477eab4c81fdfe1a84df0f
+size 4932492605

model.safetensors.index.json

@@ -0,0 +1,803 @@
+{
+    "metadata": {
+        "total_size": 54960268496
+    },
+    "weight_map": {
+        "image_newline": "model-00011-of-00011.safetensors",
+        "language_model.lm_head.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.embed_tokens.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.kv_b_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.mlp.gate.e_score_correction_bias": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.mlp.gate.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.kv_a_layernorm.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.kv_b_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.mlp.gate.e_score_correction_bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.mlp.gate.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.mlp.shared_experts.down_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.mlp.shared_experts.up_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.kv_a_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.kv_b_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.11.mlp.gate.e_score_correction_bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.11.mlp.gate.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.11.mlp.shared_experts.down_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.11.mlp.shared_experts.up_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.kv_a_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.kv_b_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.mlp.gate.e_score_correction_bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.mlp.gate.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.mlp.shared_experts.down_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.mlp.shared_experts.up_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.kv_a_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.kv_b_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.mlp.gate.e_score_correction_bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.mlp.gate.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.mlp.shared_experts.down_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.mlp.shared_experts.up_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.kv_a_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.kv_b_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.mlp.gate.e_score_correction_bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.mlp.gate.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.mlp.shared_experts.down_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.mlp.shared_experts.up_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.kv_a_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.kv_b_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.mlp.gate.e_score_correction_bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.mlp.gate.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.mlp.shared_experts.down_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.mlp.shared_experts.up_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.kv_a_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.kv_b_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.16.mlp.gate.e_score_correction_bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.16.mlp.gate.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.16.mlp.shared_experts.down_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.16.mlp.shared_experts.up_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.kv_a_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.kv_b_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.17.input_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.mlp.gate.e_score_correction_bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.mlp.gate.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.mlp.shared_experts.down_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.mlp.shared_experts.up_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.kv_a_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.kv_b_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.mlp.gate.e_score_correction_bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.mlp.gate.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.mlp.shared_experts.down_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.mlp.shared_experts.up_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.kv_a_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.kv_b_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.19.mlp.gate.e_score_correction_bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.19.mlp.gate.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.19.mlp.shared_experts.down_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.19.mlp.shared_experts.up_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.kv_a_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.kv_b_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.mlp.gate.e_score_correction_bias": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.2.mlp.gate.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.2.mlp.shared_experts.down_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.2.mlp.shared_experts.up_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.kv_a_layernorm.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.kv_b_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.layers.20.input_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.mlp.gate.e_score_correction_bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.mlp.gate.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.mlp.shared_experts.down_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.mlp.shared_experts.up_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.kv_a_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.kv_b_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.input_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.mlp.gate.e_score_correction_bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.mlp.gate.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.mlp.shared_experts.down_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.mlp.shared_experts.up_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.kv_a_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.kv_b_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.22.mlp.gate.e_score_correction_bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.22.mlp.gate.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.22.mlp.shared_experts.down_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.22.mlp.shared_experts.up_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.kv_a_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.kv_b_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.23.input_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.mlp.gate.e_score_correction_bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.mlp.gate.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.mlp.shared_experts.down_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.mlp.shared_experts.up_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.kv_a_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.kv_b_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.input_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.mlp.gate.e_score_correction_bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.mlp.gate.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.mlp.shared_experts.down_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.mlp.shared_experts.up_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.kv_a_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.kv_b_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.25.input_layernorm.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.mlp.gate.e_score_correction_bias": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.mlp.gate.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.mlp.shared_experts.down_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.mlp.shared_experts.up_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.kv_a_layernorm.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.kv_b_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.input_layernorm.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.mlp.gate.e_score_correction_bias": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.mlp.gate.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.mlp.shared_experts.down_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.mlp.shared_experts.up_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.kv_a_layernorm.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.kv_b_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.27.input_layernorm.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.27.mlp.gate.e_score_correction_bias": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.27.mlp.gate.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.27.mlp.shared_experts.down_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.27.mlp.shared_experts.up_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.27.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.kv_a_layernorm.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.kv_a_proj_with_mqa.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.kv_b_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.layers.28.input_layernorm.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.mlp.gate.e_score_correction_bias": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.mlp.gate.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.mlp.shared_experts.down_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.mlp.shared_experts.up_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.kv_a_layernorm.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.kv_a_proj_with_mqa.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.kv_b_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.input_layernorm.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.mlp.gate.e_score_correction_bias": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.mlp.gate.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.mlp.shared_experts.down_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.mlp.shared_experts.up_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.kv_a_layernorm.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.kv_a_proj_with_mqa.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.kv_b_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.mlp.gate.e_score_correction_bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.mlp.gate.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.mlp.shared_experts.down_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.mlp.shared_experts.up_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.kv_a_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.kv_b_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.mlp.gate.e_score_correction_bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.mlp.gate.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.mlp.shared_experts.down_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.mlp.shared_experts.up_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.kv_a_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.kv_b_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.mlp.gate.e_score_correction_bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.mlp.gate.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.mlp.shared_experts.down_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.mlp.shared_experts.up_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.kv_a_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.kv_b_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.mlp.gate.e_score_correction_bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.mlp.gate.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.mlp.shared_experts.down_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.mlp.shared_experts.up_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.kv_a_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.kv_b_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.mlp.gate.e_score_correction_bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.mlp.gate.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.mlp.shared_experts.down_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.mlp.shared_experts.up_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.kv_a_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.kv_b_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.8.mlp.gate.e_score_correction_bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.8.mlp.gate.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.8.mlp.shared_experts.down_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.8.mlp.shared_experts.up_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.kv_a_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.kv_b_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.mlp.gate.e_score_correction_bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.mlp.gate.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.mlp.shared_experts.down_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.mlp.shared_experts.up_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.kv_a_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.kv_b_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.norm.weight": "model-00011-of-00011.safetensors",
+        "projector.layers.0.bias": "model-00011-of-00011.safetensors",
+        "projector.layers.0.weight": "model-00011-of-00011.safetensors",
+        "projector.layers.2.bias": "model-00011-of-00011.safetensors",
+        "projector.layers.2.weight": "model-00011-of-00011.safetensors",
+        "view_separator": "model-00011-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.kv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.kv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.latent": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.norm.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.norm.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.q.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.attn_pool.q.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.0.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.0.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.0.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.0.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.0.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.0.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.0.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.0.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.1.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.1.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.1.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.1.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.1.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.1.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.1.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.1.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.10.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.10.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.10.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.10.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.10.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.10.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.10.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.10.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.11.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.11.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.11.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.11.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.11.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.11.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.11.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.11.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.12.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.12.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.12.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.12.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.12.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.12.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.12.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.12.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.12.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.12.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.13.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.13.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.13.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.13.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.13.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.13.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.13.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.13.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.13.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.13.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.14.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.14.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.14.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.14.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.14.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.14.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.14.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.14.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.14.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.14.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.15.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.15.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.15.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.15.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.15.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.15.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.15.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.15.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.15.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.15.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.16.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.16.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.16.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.16.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.16.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.16.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.16.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.16.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.16.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.16.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.17.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.17.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.17.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.17.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.17.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.17.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.17.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.17.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.17.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.17.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.18.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.18.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.18.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.18.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.18.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.18.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.18.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.18.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.18.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.18.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.19.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.19.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.19.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.19.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.19.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.19.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.19.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.19.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.19.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.19.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.2.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.2.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.2.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.2.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.2.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.2.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.2.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.2.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.20.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.20.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.20.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.20.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.20.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.20.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.20.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.20.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.20.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.21.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.21.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.21.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.21.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.21.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.21.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.21.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.21.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.21.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.22.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.22.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.22.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.22.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.22.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.22.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.22.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.22.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.22.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.23.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.23.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.23.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.23.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.23.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.23.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.23.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.23.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.23.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.24.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.24.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.24.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.24.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.24.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.24.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.24.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.24.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.24.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.24.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.24.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.24.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.25.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.25.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.25.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.25.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.25.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.25.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.25.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.25.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.25.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.25.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.25.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.25.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.26.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.26.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.26.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.26.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.26.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.26.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.26.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.26.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.26.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.26.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.26.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.26.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.3.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.3.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.3.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.3.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.3.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.3.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.3.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.3.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.4.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.4.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.4.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.4.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.4.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.4.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.4.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.4.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.5.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.5.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.5.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.5.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.5.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.5.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.5.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.5.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.6.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.6.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.6.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.6.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.6.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.6.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.6.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.6.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.7.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.7.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.7.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.7.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.7.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.7.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.7.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.7.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.8.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.8.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.8.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.8.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.8.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.8.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.8.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.8.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.9.mlp.fc1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.9.mlp.fc1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.9.mlp.fc2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.9.mlp.fc2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.9.norm1.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.9.norm1.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.9.norm2.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.blocks.9.norm2.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.norm.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.norm.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.patch_embed.proj.bias": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.patch_embed.proj.weight": "model-00001-of-00011.safetensors",
+        "vision.vision_tower.pos_embed": "model-00001-of-00011.safetensors"
+    }
+}

processor_config.json

@@ -0,0 +1,116 @@
+{
+  "add_special_token": false,
+  "candidate_resolutions": [
+    [
+      384,
+      384
+    ],
+    [
+      384,
+      768
+    ],
+    [
+      768,
+      384
+    ],
+    [
+      384,
+      1152
+    ],
+    [
+      1152,
+      384
+    ],
+    [
+      384,
+      1536
+    ],
+    [
+      1536,
+      384
+    ],
+    [
+      768,
+      768
+    ],
+    [
+      384,
+      1920
+    ],
+    [
+      1920,
+      384
+    ],
+    [
+      384,
+      2304
+    ],
+    [
+      2304,
+      384
+    ],
+    [
+      768,
+      1152
+    ],
+    [
+      1152,
+      768
+    ],
+    [
+      384,
+      2688
+    ],
+    [
+      2688,
+      384
+    ],
+    [
+      384,
+      3072
+    ],
+    [
+      3072,
+      384
+    ],
+    [
+      768,
+      1536
+    ],
+    [
+      1536,
+      768
+    ],
+    [
+      384,
+      3456
+    ],
+    [
+      3456,
+      384
+    ],
+    [
+      1152,
+      1152
+    ]
+  ],
+  "downsample_ratio": 2,
+  "ignore_id": -100,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_token": "<image>",
+  "mask_prompt": false,
+  "normalize": true,
+  "pad_token": "<\uff5c\u2581pad\u2581\uff5c>",
+  "patch_size": 14,
+  "processor_class": "DeepseekVLV2Processor",
+  "sft_format": "deepseek"
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜▁pad▁｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}