Reconvert with mlx_vlm: restore vision encoder weights

Browse files

Files changed (12) hide show

config.json +18 -2
model-00001-of-00005.safetensors +2 -2
model-00002-of-00005.safetensors +2 -2
model-00003-of-00005.safetensors +2 -2
model-00004-of-00005.safetensors +2 -2
model-00005-of-00005.safetensors +2 -2
model.safetensors.index.json +538 -206
preprocessor_config.json +21 -0
processor_config.json +63 -0
tokenizer_config.json +1 -1
video_preprocessor_config.json +21 -0
vocab.json +0 -0

config.json CHANGED Viewed

@@ -2788,14 +2788,30 @@
                 11,
                 10
             ],
             "rope_theta": 10000000,
-            "partial_rotary_factor": 0.25,
-            "type": "default"
         }
     },
     "tie_word_embeddings": false,
     "transformers_version": "4.57.0.dev0",
     "video_token_id": 248057,
     "vision_end_token_id": 248054,
     "vision_start_token_id": 248053
 }

                 11,
                 10
             ],
+            "rope_type": "default",
             "rope_theta": 10000000,
+            "partial_rotary_factor": 0.25
         }
     },
     "tie_word_embeddings": false,
     "transformers_version": "4.57.0.dev0",
     "video_token_id": 248057,
+    "vision_config": {
+        "deepstack_visual_indexes": [],
+        "depth": 27,
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_size": 1152,
+        "in_channels": 3,
+        "initializer_range": 0.02,
+        "intermediate_size": 4304,
+        "model_type": "qwen3_5_moe",
+        "num_heads": 16,
+        "num_position_embeddings": 2304,
+        "out_hidden_size": 2048,
+        "patch_size": 16,
+        "spatial_merge_size": 2,
+        "temporal_patch_size": 2
+    },
     "vision_end_token_id": 248054,
     "vision_start_token_id": 248053
 }

model-00001-of-00005.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fc2708b007a8fd67f19c6fbe79b542e637dccc89faf90db3db1e267e6fd9dee
-size 5368528684

 version https://git-lfs.github.com/spec/v1
+oid sha256:c778de5bf1869a92ccff795cd07a95fee0dec42f81fe4562332b25149f0423b7
+size 5315352133

model-00002-of-00005.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e2477d9413011ba05d543eb0e26f944ed4320964e4e92e5c966456de693e32
-size 5253397965

 version https://git-lfs.github.com/spec/v1
+oid sha256:22a511636af589803f42b4b0f7165fd53a12a315ef44058d08d1a092810fa552
+size 5361264492

model-00003-of-00005.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c070fe2305d3d324ffa5e05f6bdafdefeb23c064fd8e8482ad212bd5f1bbcea
-size 5362917750

 version https://git-lfs.github.com/spec/v1
+oid sha256:9311d31ebca816ef9a6c518d34fba8ce013fb1b970c19bf5b1542b11cc7fbf23
+size 5366331917

model-00004-of-00005.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9952b6dcae6b81aee57eb097689335b0e31a3b575e446d0915f4df4859d64ee
-size 5359430652

 version https://git-lfs.github.com/spec/v1
+oid sha256:84c32daae851e44794b8895e08572ef9ae52d0a72d0965591934bda19556c4a3
+size 5274616597

model-00005-of-00005.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f096eff8ce23d8a5001870e1c1dd14876084793ae4ffb23a604acc659adb7fa
-size 3191377916

 version https://git-lfs.github.com/spec/v1
+oid sha256:98e09fb84de86ba187cfe83992c76b698722684f54c24d5c85b7756d599ce0af
+size 4111268018

model.safetensors.index.json CHANGED Viewed

@@ -1,7 +1,6 @@
 {
     "metadata": {
-        "total_size": 24535462272,
-        "total_parameters": 34660608768
     },
     "weight_map": {
         "language_model.lm_head.weight": "model-00005-of-00005.safetensors",
@@ -352,67 +351,67 @@
         "language_model.model.layers.17.linear_attn.out_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.17.mlp.gate.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.shared_expert.down_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.shared_expert.down_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.shared_expert.down_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.shared_expert.gate_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.shared_expert.gate_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.shared_expert.up_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.shared_expert.up_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.shared_expert.up_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.shared_expert_gate.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
         "language_model.model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.A_log": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.in_proj_a.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.in_proj_a.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.in_proj_qkv.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.in_proj_qkv.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.in_proj_z.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.in_proj_z.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.out_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.out_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.gate.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.shared_expert.down_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.shared_expert.down_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.shared_expert.down_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.shared_expert.gate_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.shared_expert.gate_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.shared_expert.up_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.shared_expert.up_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.shared_expert.up_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.shared_expert_gate.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.19.mlp.gate.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.19.mlp.shared_expert.down_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.19.mlp.shared_expert.up_proj.weight": "model-00003-of-00005.safetensors",
@@ -426,15 +425,15 @@
         "language_model.model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
         "language_model.model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
         "language_model.model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.19.self_attn.q_proj.biases": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.19.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.2.linear_attn.A_log": "model-00001-of-00005.safetensors",
         "language_model.model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
@@ -754,51 +753,51 @@
         "language_model.model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
         "language_model.model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.gate.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.shared_expert.down_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.shared_expert.gate_proj.biases": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.shared_expert.gate_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.shared_expert.up_proj.biases": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.shared_expert.up_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.shared_expert.up_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.shared_expert_gate.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.A_log": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_a.biases": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_a.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_qkv.biases": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_qkv.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_z.biases": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_z.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.out_proj.biases": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.out_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.mlp.gate.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.28.mlp.shared_expert.down_proj.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.shared_expert.gate_proj.biases": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.shared_expert.gate_proj.scales": "model-00004-of-00005.safetensors",
@@ -812,13 +811,13 @@
         "language_model.model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
-        "language_model.model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.29.linear_attn.A_log": "model-00004-of-00005.safetensors",
         "language_model.model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
@@ -1046,15 +1045,15 @@
         "language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.mlp.gate.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.35.mlp.shared_expert.down_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.35.mlp.shared_expert.up_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.35.mlp.shared_expert_gate.biases": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.35.mlp.shared_expert_gate.scales": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.35.mlp.shared_expert_gate.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
@@ -1068,40 +1067,40 @@
         "language_model.model.layers.35.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.A_log": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.in_proj_a.biases": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.in_proj_a.scales": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.in_proj_b.biases": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.in_proj_b.scales": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.gate.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.shared_expert.down_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.shared_expert.up_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.shared_expert_gate.biases": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.shared_expert_gate.scales": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.shared_expert_gate.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-        "language_model.model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
         "language_model.model.layers.37.linear_attn.A_log": "model-00005-of-00005.safetensors",
-        "language_model.model.layers.37.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.37.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
         "language_model.model.layers.37.linear_attn.in_proj_a.biases": "model-00005-of-00005.safetensors",
         "language_model.model.layers.37.linear_attn.in_proj_a.scales": "model-00005-of-00005.safetensors",
@@ -1300,27 +1299,27 @@
         "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.mlp.gate.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.shared_expert.down_proj.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.shared_expert.down_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.shared_expert.down_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.shared_expert.gate_proj.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.shared_expert.gate_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.shared_expert.up_proj.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.shared_expert.up_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.shared_expert.up_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.shared_expert_gate.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.shared_expert_gate.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.shared_expert_gate.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
@@ -1330,23 +1329,23 @@
         "language_model.model.layers.7.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.A_log": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.dt_bias": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_qkv.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_qkv.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_z.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_z.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.norm.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.out_proj.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.out_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.mlp.gate.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.8.mlp.shared_expert.down_proj.biases": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.shared_expert.down_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.shared_expert.down_proj.weight": "model-00002-of-00005.safetensors",
@@ -1359,16 +1358,16 @@
         "language_model.model.layers.8.mlp.shared_expert_gate.biases": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.shared_expert_gate.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.shared_expert_gate.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-        "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.linear_attn.A_log": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
@@ -1408,6 +1407,339 @@
         "language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-        "language_model.model.norm.weight": "model-00005-of-00005.safetensors"
     }
 }

 {
     "metadata": {
+        "total_size": 25428604768
     },
     "weight_map": {
         "language_model.lm_head.weight": "model-00005-of-00005.safetensors",
         "language_model.model.layers.17.linear_attn.out_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.17.mlp.gate.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.shared_expert.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.shared_expert.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.shared_expert.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.shared_expert.gate_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.shared_expert.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.shared_expert.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.shared_expert.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.shared_expert.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.shared_expert_gate.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
         "language_model.model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
         "language_model.model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.A_log": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.dt_bias": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_a.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_a.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_qkv.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_qkv.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_z.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_z.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.norm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.out_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.out_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.gate.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.shared_expert.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.shared_expert.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.shared_expert.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.shared_expert.gate_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.shared_expert.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.shared_expert.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.shared_expert.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.shared_expert.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.shared_expert_gate.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.mlp.gate.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.19.mlp.shared_expert.down_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.19.mlp.shared_expert.up_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
         "language_model.model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
         "language_model.model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.2.linear_attn.A_log": "model-00001-of-00005.safetensors",
         "language_model.model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
         "language_model.model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
         "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.gate.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.shared_expert.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.shared_expert.gate_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.shared_expert.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.shared_expert.up_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.shared_expert.up_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.shared_expert.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.shared_expert_gate.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.A_log": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.dt_bias": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_a.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_a.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_qkv.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_qkv.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_z.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_z.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.norm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.out_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.out_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.gate.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.shared_expert.down_proj.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.shared_expert.gate_proj.biases": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.shared_expert.gate_proj.scales": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors",
         "language_model.model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.29.linear_attn.A_log": "model-00004-of-00005.safetensors",
         "language_model.model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.mlp.gate.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.shared_expert.down_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.shared_expert.up_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.shared_expert_gate.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.shared_expert_gate.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.shared_expert_gate.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00005-of-00005.safetensors",
         "language_model.model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
         "language_model.model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.A_log": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.in_proj_a.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.in_proj_a.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.in_proj_a.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.in_proj_b.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.in_proj_b.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.in_proj_b.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.in_proj_qkv.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.in_proj_z.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.norm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.linear_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.gate.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.shared_expert.down_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.shared_expert.up_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.shared_expert_gate.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.shared_expert_gate.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.shared_expert_gate.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
         "language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
         "language_model.model.layers.37.linear_attn.A_log": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.linear_attn.conv1d.weight": "model-00005-of-00005.safetensors",
         "language_model.model.layers.37.linear_attn.dt_bias": "model-00005-of-00005.safetensors",
         "language_model.model.layers.37.linear_attn.in_proj_a.biases": "model-00005-of-00005.safetensors",
         "language_model.model.layers.37.linear_attn.in_proj_a.scales": "model-00005-of-00005.safetensors",
         "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.mlp.gate.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.shared_expert.down_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.shared_expert.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.shared_expert.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.shared_expert.gate_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.shared_expert.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.shared_expert.up_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.shared_expert.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.shared_expert.up_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.shared_expert_gate.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.shared_expert_gate.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.shared_expert_gate.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
         "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.A_log": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.dt_bias": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_qkv.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_qkv.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_z.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_z.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.norm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.out_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.out_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.gate.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.shared_expert.down_proj.biases": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.shared_expert.down_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.shared_expert.down_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.shared_expert_gate.biases": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.shared_expert_gate.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.8.mlp.shared_expert_gate.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.linear_attn.A_log": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
         "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.norm.weight": "model-00005-of-00005.safetensors",
+        "vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.0.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.0.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.0.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.0.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.1.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.1.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.1.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.1.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.10.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.10.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.10.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.10.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.11.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.11.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.11.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.11.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.12.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.12.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.12.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.12.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.12.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.12.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.13.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.13.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.13.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.13.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.13.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.13.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.14.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.14.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.14.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.14.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.14.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.14.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.15.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.15.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.15.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.15.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.15.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.15.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.16.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.16.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.16.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.16.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.16.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.16.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.17.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.17.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.17.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.17.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.17.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.17.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.18.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.18.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.18.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.18.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.18.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.18.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.19.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.19.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.19.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.19.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.19.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.19.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.2.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.2.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.2.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.2.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.20.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.20.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.20.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.20.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.20.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.21.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.21.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.21.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.21.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.21.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.22.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.22.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.22.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.22.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.22.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.23.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.23.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.23.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.23.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.23.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.24.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.24.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.24.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.24.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.24.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.24.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.24.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.24.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.25.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.25.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.25.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.25.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.25.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.25.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.25.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.25.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.26.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.26.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.26.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.26.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.26.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.26.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.26.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.26.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.3.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.3.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.3.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.3.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.4.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.4.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.4.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.4.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.5.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.5.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.5.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.5.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.6.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.6.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.6.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.6.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.7.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.7.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.7.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.7.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.8.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.8.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.8.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.8.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.9.norm1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.9.norm1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.9.norm2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.blocks.9.norm2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.merger.linear_fc1.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.merger.linear_fc1.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.merger.linear_fc2.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.merger.linear_fc2.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.merger.norm.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.merger.norm.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.patch_embed.proj.bias": "model-00001-of-00005.safetensors",
+        "vision_tower.patch_embed.proj.weight": "model-00001-of-00005.safetensors",
+        "vision_tower.pos_embed.weight": "model-00001-of-00005.safetensors"
     }
 }

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

processor_config.json ADDED Viewed

	@@ -0,0 +1,63 @@

+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer_config.json CHANGED Viewed

@@ -22,9 +22,9 @@
   },
   "pad_token": "<|endoftext|>",
   "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
   "split_special_tokens": false,
   "tokenizer_class": "TokenizersBackend",
-  "tool_parser_type": "qwen3_coder",
   "unk_token": null,
   "video_token": "<|video_pad|>",
   "vision_bos_token": "<|vision_start|>",

   },
   "pad_token": "<|endoftext|>",
   "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "TokenizersBackend",
   "unk_token": null,
   "video_token": "<|video_pad|>",
   "vision_bos_token": "<|vision_start|>",

video_preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff