Upload 6 files

.gitattributes

@@ -39,3 +39,4 @@ Qwen-3-8B/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Qwen-3-4B/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Mistral-3-Small/tekken.json filter=lfs diff=lfs merge=lfs -text
 AceStepXL/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen-3-VL/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Qwen-3-VL/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

Qwen-3-VL/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen3VLModel"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.8.0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "ideogram_fp8_weight_only": true
+}

Qwen-3-VL/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b094e8be345fc602b79eae674004cf44078e511f03d200980095244a0d1bcf46
+size 8779278400

Qwen-3-VL/model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 8779147168}, "weight_map": {"language_model.embed_tokens.weight": "model.safetensors", "language_model.layers.0.input_layernorm.weight": "model.safetensors", "language_model.layers.0.mlp.down_proj.weight": "model.safetensors", "language_model.layers.0.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.0.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.0.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.0.mlp.up_proj.weight": "model.safetensors", "language_model.layers.0.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.0.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.0.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.0.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.0.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.0.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.0.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.0.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.0.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.0.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.0.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.0.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.1.input_layernorm.weight": "model.safetensors", "language_model.layers.1.mlp.down_proj.weight": "model.safetensors", "language_model.layers.1.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.1.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.1.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.1.mlp.up_proj.weight": "model.safetensors", "language_model.layers.1.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.1.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.1.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.1.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.1.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.1.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.1.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.1.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.1.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.1.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.1.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.1.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.10.input_layernorm.weight": "model.safetensors", "language_model.layers.10.mlp.down_proj.weight": "model.safetensors", "language_model.layers.10.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.10.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.10.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.10.mlp.up_proj.weight": "model.safetensors", "language_model.layers.10.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.10.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.10.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.10.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.10.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.10.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.10.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.10.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.10.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.10.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.10.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.10.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.11.input_layernorm.weight": "model.safetensors", "language_model.layers.11.mlp.down_proj.weight": "model.safetensors", "language_model.layers.11.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.11.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.11.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.11.mlp.up_proj.weight": "model.safetensors", "language_model.layers.11.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.11.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.11.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.11.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.11.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.11.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.11.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.11.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.11.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.11.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.11.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.11.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.12.input_layernorm.weight": "model.safetensors", "language_model.layers.12.mlp.down_proj.weight": "model.safetensors", "language_model.layers.12.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.12.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.12.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.12.mlp.up_proj.weight": "model.safetensors", "language_model.layers.12.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.12.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.12.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.12.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.12.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.12.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.12.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.12.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.12.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.12.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.12.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.12.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.13.input_layernorm.weight": "model.safetensors", "language_model.layers.13.mlp.down_proj.weight": "model.safetensors", "language_model.layers.13.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.13.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.13.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.13.mlp.up_proj.weight": "model.safetensors", "language_model.layers.13.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.13.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.13.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.13.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.13.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.13.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.13.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.13.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.13.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.13.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.13.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.13.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.14.input_layernorm.weight": "model.safetensors", "language_model.layers.14.mlp.down_proj.weight": "model.safetensors", "language_model.layers.14.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.14.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.14.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.14.mlp.up_proj.weight": "model.safetensors", "language_model.layers.14.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.14.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.14.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.14.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.14.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.14.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.14.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.14.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.14.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.14.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.14.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.14.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.15.input_layernorm.weight": "model.safetensors", "language_model.layers.15.mlp.down_proj.weight": "model.safetensors", "language_model.layers.15.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.15.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.15.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.15.mlp.up_proj.weight": "model.safetensors", "language_model.layers.15.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.15.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.15.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.15.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.15.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.15.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.15.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.15.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.15.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.15.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.15.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.15.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.16.input_layernorm.weight": "model.safetensors", "language_model.layers.16.mlp.down_proj.weight": "model.safetensors", "language_model.layers.16.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.16.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.16.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.16.mlp.up_proj.weight": "model.safetensors", "language_model.layers.16.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.16.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.16.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.16.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.16.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.16.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.16.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.16.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.16.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.16.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.16.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.16.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.17.input_layernorm.weight": "model.safetensors", "language_model.layers.17.mlp.down_proj.weight": "model.safetensors", "language_model.layers.17.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.17.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.17.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.17.mlp.up_proj.weight": "model.safetensors", "language_model.layers.17.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.17.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.17.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.17.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.17.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.17.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.17.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.17.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.17.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.17.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.17.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.17.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.18.input_layernorm.weight": "model.safetensors", "language_model.layers.18.mlp.down_proj.weight": "model.safetensors", "language_model.layers.18.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.18.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.18.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.18.mlp.up_proj.weight": "model.safetensors", "language_model.layers.18.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.18.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.18.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.18.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.18.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.18.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.18.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.18.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.18.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.18.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.18.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.18.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.19.input_layernorm.weight": "model.safetensors", "language_model.layers.19.mlp.down_proj.weight": "model.safetensors", "language_model.layers.19.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.19.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.19.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.19.mlp.up_proj.weight": "model.safetensors", "language_model.layers.19.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.19.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.19.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.19.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.19.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.19.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.19.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.19.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.19.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.19.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.19.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.19.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.2.input_layernorm.weight": "model.safetensors", "language_model.layers.2.mlp.down_proj.weight": "model.safetensors", "language_model.layers.2.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.2.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.2.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.2.mlp.up_proj.weight": "model.safetensors", "language_model.layers.2.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.2.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.2.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.2.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.2.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.2.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.2.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.2.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.2.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.2.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.2.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.2.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.20.input_layernorm.weight": "model.safetensors", "language_model.layers.20.mlp.down_proj.weight": "model.safetensors", "language_model.layers.20.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.20.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.20.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.20.mlp.up_proj.weight": "model.safetensors", "language_model.layers.20.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.20.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.20.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.20.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.20.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.20.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.20.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.20.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.20.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.20.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.20.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.20.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.21.input_layernorm.weight": "model.safetensors", "language_model.layers.21.mlp.down_proj.weight": "model.safetensors", "language_model.layers.21.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.21.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.21.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.21.mlp.up_proj.weight": "model.safetensors", "language_model.layers.21.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.21.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.21.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.21.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.21.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.21.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.21.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.21.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.21.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.21.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.21.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.21.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.22.input_layernorm.weight": "model.safetensors", "language_model.layers.22.mlp.down_proj.weight": "model.safetensors", "language_model.layers.22.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.22.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.22.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.22.mlp.up_proj.weight": "model.safetensors", "language_model.layers.22.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.22.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.22.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.22.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.22.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.22.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.22.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.22.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.22.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.22.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.22.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.22.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.23.input_layernorm.weight": "model.safetensors", "language_model.layers.23.mlp.down_proj.weight": "model.safetensors", "language_model.layers.23.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.23.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.23.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.23.mlp.up_proj.weight": "model.safetensors", "language_model.layers.23.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.23.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.23.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.23.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.23.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.23.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.23.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.23.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.23.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.23.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.23.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.23.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.24.input_layernorm.weight": "model.safetensors", "language_model.layers.24.mlp.down_proj.weight": "model.safetensors", "language_model.layers.24.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.24.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.24.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.24.mlp.up_proj.weight": "model.safetensors", "language_model.layers.24.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.24.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.24.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.24.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.24.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.24.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.24.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.24.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.24.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.24.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.24.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.24.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.25.input_layernorm.weight": "model.safetensors", "language_model.layers.25.mlp.down_proj.weight": "model.safetensors", "language_model.layers.25.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.25.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.25.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.25.mlp.up_proj.weight": "model.safetensors", "language_model.layers.25.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.25.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.25.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.25.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.25.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.25.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.25.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.25.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.25.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.25.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.25.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.25.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.26.input_layernorm.weight": "model.safetensors", "language_model.layers.26.mlp.down_proj.weight": "model.safetensors", "language_model.layers.26.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.26.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.26.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.26.mlp.up_proj.weight": "model.safetensors", "language_model.layers.26.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.26.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.26.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.26.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.26.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.26.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.26.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.26.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.26.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.26.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.26.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.26.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.27.input_layernorm.weight": "model.safetensors", "language_model.layers.27.mlp.down_proj.weight": "model.safetensors", "language_model.layers.27.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.27.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.27.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.27.mlp.up_proj.weight": "model.safetensors", "language_model.layers.27.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.27.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.27.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.27.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.27.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.27.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.27.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.27.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.27.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.27.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.27.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.27.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.28.input_layernorm.weight": "model.safetensors", "language_model.layers.28.mlp.down_proj.weight": "model.safetensors", "language_model.layers.28.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.28.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.28.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.28.mlp.up_proj.weight": "model.safetensors", "language_model.layers.28.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.28.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.28.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.28.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.28.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.28.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.28.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.28.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.28.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.28.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.28.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.28.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.29.input_layernorm.weight": "model.safetensors", "language_model.layers.29.mlp.down_proj.weight": "model.safetensors", "language_model.layers.29.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.29.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.29.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.29.mlp.up_proj.weight": "model.safetensors", "language_model.layers.29.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.29.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.29.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.29.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.29.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.29.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.29.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.29.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.29.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.29.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.29.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.29.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.3.input_layernorm.weight": "model.safetensors", "language_model.layers.3.mlp.down_proj.weight": "model.safetensors", "language_model.layers.3.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.3.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.3.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.3.mlp.up_proj.weight": "model.safetensors", "language_model.layers.3.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.3.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.3.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.3.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.3.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.3.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.3.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.3.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.3.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.3.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.3.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.3.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.30.input_layernorm.weight": "model.safetensors", "language_model.layers.30.mlp.down_proj.weight": "model.safetensors", "language_model.layers.30.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.30.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.30.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.30.mlp.up_proj.weight": "model.safetensors", "language_model.layers.30.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.30.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.30.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.30.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.30.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.30.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.30.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.30.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.30.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.30.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.30.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.30.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.31.input_layernorm.weight": "model.safetensors", "language_model.layers.31.mlp.down_proj.weight": "model.safetensors", "language_model.layers.31.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.31.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.31.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.31.mlp.up_proj.weight": "model.safetensors", "language_model.layers.31.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.31.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.31.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.31.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.31.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.31.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.31.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.31.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.31.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.31.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.31.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.31.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.32.input_layernorm.weight": "model.safetensors", "language_model.layers.32.mlp.down_proj.weight": "model.safetensors", "language_model.layers.32.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.32.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.32.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.32.mlp.up_proj.weight": "model.safetensors", "language_model.layers.32.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.32.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.32.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.32.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.32.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.32.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.32.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.32.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.32.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.32.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.32.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.32.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.33.input_layernorm.weight": "model.safetensors", "language_model.layers.33.mlp.down_proj.weight": "model.safetensors", "language_model.layers.33.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.33.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.33.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.33.mlp.up_proj.weight": "model.safetensors", "language_model.layers.33.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.33.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.33.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.33.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.33.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.33.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.33.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.33.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.33.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.33.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.33.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.33.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.34.input_layernorm.weight": "model.safetensors", "language_model.layers.34.mlp.down_proj.weight": "model.safetensors", "language_model.layers.34.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.34.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.34.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.34.mlp.up_proj.weight": "model.safetensors", "language_model.layers.34.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.34.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.34.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.34.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.34.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.34.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.34.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.34.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.34.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.34.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.34.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.34.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.35.input_layernorm.weight": "model.safetensors", "language_model.layers.35.mlp.down_proj.weight": "model.safetensors", "language_model.layers.35.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.35.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.35.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.35.mlp.up_proj.weight": "model.safetensors", "language_model.layers.35.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.35.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.35.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.35.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.35.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.35.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.35.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.35.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.35.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.35.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.35.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.35.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.4.input_layernorm.weight": "model.safetensors", "language_model.layers.4.mlp.down_proj.weight": "model.safetensors", "language_model.layers.4.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.4.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.4.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.4.mlp.up_proj.weight": "model.safetensors", "language_model.layers.4.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.4.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.4.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.4.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.4.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.4.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.4.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.4.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.4.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.4.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.4.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.4.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.5.input_layernorm.weight": "model.safetensors", "language_model.layers.5.mlp.down_proj.weight": "model.safetensors", "language_model.layers.5.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.5.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.5.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.5.mlp.up_proj.weight": "model.safetensors", "language_model.layers.5.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.5.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.5.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.5.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.5.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.5.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.5.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.5.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.5.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.5.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.5.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.5.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.6.input_layernorm.weight": "model.safetensors", "language_model.layers.6.mlp.down_proj.weight": "model.safetensors", "language_model.layers.6.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.6.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.6.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.6.mlp.up_proj.weight": "model.safetensors", "language_model.layers.6.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.6.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.6.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.6.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.6.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.6.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.6.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.6.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.6.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.6.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.6.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.6.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.7.input_layernorm.weight": "model.safetensors", "language_model.layers.7.mlp.down_proj.weight": "model.safetensors", "language_model.layers.7.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.7.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.7.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.7.mlp.up_proj.weight": "model.safetensors", "language_model.layers.7.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.7.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.7.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.7.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.7.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.7.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.7.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.7.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.7.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.7.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.7.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.7.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.8.input_layernorm.weight": "model.safetensors", "language_model.layers.8.mlp.down_proj.weight": "model.safetensors", "language_model.layers.8.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.8.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.8.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.8.mlp.up_proj.weight": "model.safetensors", "language_model.layers.8.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.8.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.8.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.8.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.8.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.8.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.8.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.8.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.8.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.8.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.8.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.8.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.layers.9.input_layernorm.weight": "model.safetensors", "language_model.layers.9.mlp.down_proj.weight": "model.safetensors", "language_model.layers.9.mlp.down_proj.weight_scale": "model.safetensors", "language_model.layers.9.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.9.mlp.gate_proj.weight_scale": "model.safetensors", "language_model.layers.9.mlp.up_proj.weight": "model.safetensors", "language_model.layers.9.mlp.up_proj.weight_scale": "model.safetensors", "language_model.layers.9.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.9.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.9.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.9.self_attn.k_proj.weight_scale": "model.safetensors", "language_model.layers.9.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.9.self_attn.o_proj.weight_scale": "model.safetensors", "language_model.layers.9.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.9.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.9.self_attn.q_proj.weight_scale": "model.safetensors", "language_model.layers.9.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.9.self_attn.v_proj.weight_scale": "model.safetensors", "language_model.norm.weight": "model.safetensors", "visual.blocks.0.attn.proj.bias": "model.safetensors", "visual.blocks.0.attn.proj.weight": "model.safetensors", "visual.blocks.0.attn.proj.weight_scale": "model.safetensors", "visual.blocks.0.attn.qkv.bias": "model.safetensors", "visual.blocks.0.attn.qkv.weight": "model.safetensors", "visual.blocks.0.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.0.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.0.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.0.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.0.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.0.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.0.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.0.norm1.bias": "model.safetensors", "visual.blocks.0.norm1.weight": "model.safetensors", "visual.blocks.0.norm2.bias": "model.safetensors", "visual.blocks.0.norm2.weight": "model.safetensors", "visual.blocks.1.attn.proj.bias": "model.safetensors", "visual.blocks.1.attn.proj.weight": "model.safetensors", "visual.blocks.1.attn.proj.weight_scale": "model.safetensors", "visual.blocks.1.attn.qkv.bias": "model.safetensors", "visual.blocks.1.attn.qkv.weight": "model.safetensors", "visual.blocks.1.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.1.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.1.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.1.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.1.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.1.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.1.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.1.norm1.bias": "model.safetensors", "visual.blocks.1.norm1.weight": "model.safetensors", "visual.blocks.1.norm2.bias": "model.safetensors", "visual.blocks.1.norm2.weight": "model.safetensors", "visual.blocks.10.attn.proj.bias": "model.safetensors", "visual.blocks.10.attn.proj.weight": "model.safetensors", "visual.blocks.10.attn.proj.weight_scale": "model.safetensors", "visual.blocks.10.attn.qkv.bias": "model.safetensors", "visual.blocks.10.attn.qkv.weight": "model.safetensors", "visual.blocks.10.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.10.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.10.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.10.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.10.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.10.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.10.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.10.norm1.bias": "model.safetensors", "visual.blocks.10.norm1.weight": "model.safetensors", "visual.blocks.10.norm2.bias": "model.safetensors", "visual.blocks.10.norm2.weight": "model.safetensors", "visual.blocks.11.attn.proj.bias": "model.safetensors", "visual.blocks.11.attn.proj.weight": "model.safetensors", "visual.blocks.11.attn.proj.weight_scale": "model.safetensors", "visual.blocks.11.attn.qkv.bias": "model.safetensors", "visual.blocks.11.attn.qkv.weight": "model.safetensors", "visual.blocks.11.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.11.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.11.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.11.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.11.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.11.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.11.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.11.norm1.bias": "model.safetensors", "visual.blocks.11.norm1.weight": "model.safetensors", "visual.blocks.11.norm2.bias": "model.safetensors", "visual.blocks.11.norm2.weight": "model.safetensors", "visual.blocks.12.attn.proj.bias": "model.safetensors", "visual.blocks.12.attn.proj.weight": "model.safetensors", "visual.blocks.12.attn.proj.weight_scale": "model.safetensors", "visual.blocks.12.attn.qkv.bias": "model.safetensors", "visual.blocks.12.attn.qkv.weight": "model.safetensors", "visual.blocks.12.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.12.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.12.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.12.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.12.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.12.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.12.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.12.norm1.bias": "model.safetensors", "visual.blocks.12.norm1.weight": "model.safetensors", "visual.blocks.12.norm2.bias": "model.safetensors", "visual.blocks.12.norm2.weight": "model.safetensors", "visual.blocks.13.attn.proj.bias": "model.safetensors", "visual.blocks.13.attn.proj.weight": "model.safetensors", "visual.blocks.13.attn.proj.weight_scale": "model.safetensors", "visual.blocks.13.attn.qkv.bias": "model.safetensors", "visual.blocks.13.attn.qkv.weight": "model.safetensors", "visual.blocks.13.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.13.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.13.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.13.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.13.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.13.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.13.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.13.norm1.bias": "model.safetensors", "visual.blocks.13.norm1.weight": "model.safetensors", "visual.blocks.13.norm2.bias": "model.safetensors", "visual.blocks.13.norm2.weight": "model.safetensors", "visual.blocks.14.attn.proj.bias": "model.safetensors", "visual.blocks.14.attn.proj.weight": "model.safetensors", "visual.blocks.14.attn.proj.weight_scale": "model.safetensors", "visual.blocks.14.attn.qkv.bias": "model.safetensors", "visual.blocks.14.attn.qkv.weight": "model.safetensors", "visual.blocks.14.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.14.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.14.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.14.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.14.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.14.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.14.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.14.norm1.bias": "model.safetensors", "visual.blocks.14.norm1.weight": "model.safetensors", "visual.blocks.14.norm2.bias": "model.safetensors", "visual.blocks.14.norm2.weight": "model.safetensors", "visual.blocks.15.attn.proj.bias": "model.safetensors", "visual.blocks.15.attn.proj.weight": "model.safetensors", "visual.blocks.15.attn.proj.weight_scale": "model.safetensors", "visual.blocks.15.attn.qkv.bias": "model.safetensors", "visual.blocks.15.attn.qkv.weight": "model.safetensors", "visual.blocks.15.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.15.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.15.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.15.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.15.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.15.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.15.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.15.norm1.bias": "model.safetensors", "visual.blocks.15.norm1.weight": "model.safetensors", "visual.blocks.15.norm2.bias": "model.safetensors", "visual.blocks.15.norm2.weight": "model.safetensors", "visual.blocks.16.attn.proj.bias": "model.safetensors", "visual.blocks.16.attn.proj.weight": "model.safetensors", "visual.blocks.16.attn.proj.weight_scale": "model.safetensors", "visual.blocks.16.attn.qkv.bias": "model.safetensors", "visual.blocks.16.attn.qkv.weight": "model.safetensors", "visual.blocks.16.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.16.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.16.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.16.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.16.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.16.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.16.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.16.norm1.bias": "model.safetensors", "visual.blocks.16.norm1.weight": "model.safetensors", "visual.blocks.16.norm2.bias": "model.safetensors", "visual.blocks.16.norm2.weight": "model.safetensors", "visual.blocks.17.attn.proj.bias": "model.safetensors", "visual.blocks.17.attn.proj.weight": "model.safetensors", "visual.blocks.17.attn.proj.weight_scale": "model.safetensors", "visual.blocks.17.attn.qkv.bias": "model.safetensors", "visual.blocks.17.attn.qkv.weight": "model.safetensors", "visual.blocks.17.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.17.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.17.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.17.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.17.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.17.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.17.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.17.norm1.bias": "model.safetensors", "visual.blocks.17.norm1.weight": "model.safetensors", "visual.blocks.17.norm2.bias": "model.safetensors", "visual.blocks.17.norm2.weight": "model.safetensors", "visual.blocks.18.attn.proj.bias": "model.safetensors", "visual.blocks.18.attn.proj.weight": "model.safetensors", "visual.blocks.18.attn.proj.weight_scale": "model.safetensors", "visual.blocks.18.attn.qkv.bias": "model.safetensors", "visual.blocks.18.attn.qkv.weight": "model.safetensors", "visual.blocks.18.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.18.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.18.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.18.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.18.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.18.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.18.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.18.norm1.bias": "model.safetensors", "visual.blocks.18.norm1.weight": "model.safetensors", "visual.blocks.18.norm2.bias": "model.safetensors", "visual.blocks.18.norm2.weight": "model.safetensors", "visual.blocks.19.attn.proj.bias": "model.safetensors", "visual.blocks.19.attn.proj.weight": "model.safetensors", "visual.blocks.19.attn.proj.weight_scale": "model.safetensors", "visual.blocks.19.attn.qkv.bias": "model.safetensors", "visual.blocks.19.attn.qkv.weight": "model.safetensors", "visual.blocks.19.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.19.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.19.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.19.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.19.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.19.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.19.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.19.norm1.bias": "model.safetensors", "visual.blocks.19.norm1.weight": "model.safetensors", "visual.blocks.19.norm2.bias": "model.safetensors", "visual.blocks.19.norm2.weight": "model.safetensors", "visual.blocks.2.attn.proj.bias": "model.safetensors", "visual.blocks.2.attn.proj.weight": "model.safetensors", "visual.blocks.2.attn.proj.weight_scale": "model.safetensors", "visual.blocks.2.attn.qkv.bias": "model.safetensors", "visual.blocks.2.attn.qkv.weight": "model.safetensors", "visual.blocks.2.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.2.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.2.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.2.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.2.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.2.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.2.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.2.norm1.bias": "model.safetensors", "visual.blocks.2.norm1.weight": "model.safetensors", "visual.blocks.2.norm2.bias": "model.safetensors", "visual.blocks.2.norm2.weight": "model.safetensors", "visual.blocks.20.attn.proj.bias": "model.safetensors", "visual.blocks.20.attn.proj.weight": "model.safetensors", "visual.blocks.20.attn.proj.weight_scale": "model.safetensors", "visual.blocks.20.attn.qkv.bias": "model.safetensors", "visual.blocks.20.attn.qkv.weight": "model.safetensors", "visual.blocks.20.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.20.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.20.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.20.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.20.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.20.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.20.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.20.norm1.bias": "model.safetensors", "visual.blocks.20.norm1.weight": "model.safetensors", "visual.blocks.20.norm2.bias": "model.safetensors", "visual.blocks.20.norm2.weight": "model.safetensors", "visual.blocks.21.attn.proj.bias": "model.safetensors", "visual.blocks.21.attn.proj.weight": "model.safetensors", "visual.blocks.21.attn.proj.weight_scale": "model.safetensors", "visual.blocks.21.attn.qkv.bias": "model.safetensors", "visual.blocks.21.attn.qkv.weight": "model.safetensors", "visual.blocks.21.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.21.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.21.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.21.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.21.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.21.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.21.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.21.norm1.bias": "model.safetensors", "visual.blocks.21.norm1.weight": "model.safetensors", "visual.blocks.21.norm2.bias": "model.safetensors", "visual.blocks.21.norm2.weight": "model.safetensors", "visual.blocks.22.attn.proj.bias": "model.safetensors", "visual.blocks.22.attn.proj.weight": "model.safetensors", "visual.blocks.22.attn.proj.weight_scale": "model.safetensors", "visual.blocks.22.attn.qkv.bias": "model.safetensors", "visual.blocks.22.attn.qkv.weight": "model.safetensors", "visual.blocks.22.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.22.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.22.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.22.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.22.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.22.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.22.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.22.norm1.bias": "model.safetensors", "visual.blocks.22.norm1.weight": "model.safetensors", "visual.blocks.22.norm2.bias": "model.safetensors", "visual.blocks.22.norm2.weight": "model.safetensors", "visual.blocks.23.attn.proj.bias": "model.safetensors", "visual.blocks.23.attn.proj.weight": "model.safetensors", "visual.blocks.23.attn.proj.weight_scale": "model.safetensors", "visual.blocks.23.attn.qkv.bias": "model.safetensors", "visual.blocks.23.attn.qkv.weight": "model.safetensors", "visual.blocks.23.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.23.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.23.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.23.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.23.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.23.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.23.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.23.norm1.bias": "model.safetensors", "visual.blocks.23.norm1.weight": "model.safetensors", "visual.blocks.23.norm2.bias": "model.safetensors", "visual.blocks.23.norm2.weight": "model.safetensors", "visual.blocks.24.attn.proj.bias": "model.safetensors", "visual.blocks.24.attn.proj.weight": "model.safetensors", "visual.blocks.24.attn.proj.weight_scale": "model.safetensors", "visual.blocks.24.attn.qkv.bias": "model.safetensors", "visual.blocks.24.attn.qkv.weight": "model.safetensors", "visual.blocks.24.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.24.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.24.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.24.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.24.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.24.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.24.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.24.norm1.bias": "model.safetensors", "visual.blocks.24.norm1.weight": "model.safetensors", "visual.blocks.24.norm2.bias": "model.safetensors", "visual.blocks.24.norm2.weight": "model.safetensors", "visual.blocks.25.attn.proj.bias": "model.safetensors", "visual.blocks.25.attn.proj.weight": "model.safetensors", "visual.blocks.25.attn.proj.weight_scale": "model.safetensors", "visual.blocks.25.attn.qkv.bias": "model.safetensors", "visual.blocks.25.attn.qkv.weight": "model.safetensors", "visual.blocks.25.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.25.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.25.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.25.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.25.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.25.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.25.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.25.norm1.bias": "model.safetensors", "visual.blocks.25.norm1.weight": "model.safetensors", "visual.blocks.25.norm2.bias": "model.safetensors", "visual.blocks.25.norm2.weight": "model.safetensors", "visual.blocks.26.attn.proj.bias": "model.safetensors", "visual.blocks.26.attn.proj.weight": "model.safetensors", "visual.blocks.26.attn.proj.weight_scale": "model.safetensors", "visual.blocks.26.attn.qkv.bias": "model.safetensors", "visual.blocks.26.attn.qkv.weight": "model.safetensors", "visual.blocks.26.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.26.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.26.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.26.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.26.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.26.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.26.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.26.norm1.bias": "model.safetensors", "visual.blocks.26.norm1.weight": "model.safetensors", "visual.blocks.26.norm2.bias": "model.safetensors", "visual.blocks.26.norm2.weight": "model.safetensors", "visual.blocks.3.attn.proj.bias": "model.safetensors", "visual.blocks.3.attn.proj.weight": "model.safetensors", "visual.blocks.3.attn.proj.weight_scale": "model.safetensors", "visual.blocks.3.attn.qkv.bias": "model.safetensors", "visual.blocks.3.attn.qkv.weight": "model.safetensors", "visual.blocks.3.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.3.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.3.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.3.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.3.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.3.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.3.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.3.norm1.bias": "model.safetensors", "visual.blocks.3.norm1.weight": "model.safetensors", "visual.blocks.3.norm2.bias": "model.safetensors", "visual.blocks.3.norm2.weight": "model.safetensors", "visual.blocks.4.attn.proj.bias": "model.safetensors", "visual.blocks.4.attn.proj.weight": "model.safetensors", "visual.blocks.4.attn.proj.weight_scale": "model.safetensors", "visual.blocks.4.attn.qkv.bias": "model.safetensors", "visual.blocks.4.attn.qkv.weight": "model.safetensors", "visual.blocks.4.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.4.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.4.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.4.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.4.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.4.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.4.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.4.norm1.bias": "model.safetensors", "visual.blocks.4.norm1.weight": "model.safetensors", "visual.blocks.4.norm2.bias": "model.safetensors", "visual.blocks.4.norm2.weight": "model.safetensors", "visual.blocks.5.attn.proj.bias": "model.safetensors", "visual.blocks.5.attn.proj.weight": "model.safetensors", "visual.blocks.5.attn.proj.weight_scale": "model.safetensors", "visual.blocks.5.attn.qkv.bias": "model.safetensors", "visual.blocks.5.attn.qkv.weight": "model.safetensors", "visual.blocks.5.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.5.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.5.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.5.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.5.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.5.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.5.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.5.norm1.bias": "model.safetensors", "visual.blocks.5.norm1.weight": "model.safetensors", "visual.blocks.5.norm2.bias": "model.safetensors", "visual.blocks.5.norm2.weight": "model.safetensors", "visual.blocks.6.attn.proj.bias": "model.safetensors", "visual.blocks.6.attn.proj.weight": "model.safetensors", "visual.blocks.6.attn.proj.weight_scale": "model.safetensors", "visual.blocks.6.attn.qkv.bias": "model.safetensors", "visual.blocks.6.attn.qkv.weight": "model.safetensors", "visual.blocks.6.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.6.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.6.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.6.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.6.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.6.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.6.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.6.norm1.bias": "model.safetensors", "visual.blocks.6.norm1.weight": "model.safetensors", "visual.blocks.6.norm2.bias": "model.safetensors", "visual.blocks.6.norm2.weight": "model.safetensors", "visual.blocks.7.attn.proj.bias": "model.safetensors", "visual.blocks.7.attn.proj.weight": "model.safetensors", "visual.blocks.7.attn.proj.weight_scale": "model.safetensors", "visual.blocks.7.attn.qkv.bias": "model.safetensors", "visual.blocks.7.attn.qkv.weight": "model.safetensors", "visual.blocks.7.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.7.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.7.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.7.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.7.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.7.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.7.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.7.norm1.bias": "model.safetensors", "visual.blocks.7.norm1.weight": "model.safetensors", "visual.blocks.7.norm2.bias": "model.safetensors", "visual.blocks.7.norm2.weight": "model.safetensors", "visual.blocks.8.attn.proj.bias": "model.safetensors", "visual.blocks.8.attn.proj.weight": "model.safetensors", "visual.blocks.8.attn.proj.weight_scale": "model.safetensors", "visual.blocks.8.attn.qkv.bias": "model.safetensors", "visual.blocks.8.attn.qkv.weight": "model.safetensors", "visual.blocks.8.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.8.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.8.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.8.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.8.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.8.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.8.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.8.norm1.bias": "model.safetensors", "visual.blocks.8.norm1.weight": "model.safetensors", "visual.blocks.8.norm2.bias": "model.safetensors", "visual.blocks.8.norm2.weight": "model.safetensors", "visual.blocks.9.attn.proj.bias": "model.safetensors", "visual.blocks.9.attn.proj.weight": "model.safetensors", "visual.blocks.9.attn.proj.weight_scale": "model.safetensors", "visual.blocks.9.attn.qkv.bias": "model.safetensors", "visual.blocks.9.attn.qkv.weight": "model.safetensors", "visual.blocks.9.attn.qkv.weight_scale": "model.safetensors", "visual.blocks.9.mlp.linear_fc1.bias": "model.safetensors", "visual.blocks.9.mlp.linear_fc1.weight": "model.safetensors", "visual.blocks.9.mlp.linear_fc1.weight_scale": "model.safetensors", "visual.blocks.9.mlp.linear_fc2.bias": "model.safetensors", "visual.blocks.9.mlp.linear_fc2.weight": "model.safetensors", "visual.blocks.9.mlp.linear_fc2.weight_scale": "model.safetensors", "visual.blocks.9.norm1.bias": "model.safetensors", "visual.blocks.9.norm1.weight": "model.safetensors", "visual.blocks.9.norm2.bias": "model.safetensors", "visual.blocks.9.norm2.weight": "model.safetensors", "visual.deepstack_merger_list.0.linear_fc1.bias": "model.safetensors", "visual.deepstack_merger_list.0.linear_fc1.weight": "model.safetensors", "visual.deepstack_merger_list.0.linear_fc1.weight_scale": "model.safetensors", "visual.deepstack_merger_list.0.linear_fc2.bias": "model.safetensors", "visual.deepstack_merger_list.0.linear_fc2.weight": "model.safetensors", "visual.deepstack_merger_list.0.linear_fc2.weight_scale": "model.safetensors", "visual.deepstack_merger_list.0.norm.bias": "model.safetensors", "visual.deepstack_merger_list.0.norm.weight": "model.safetensors", "visual.deepstack_merger_list.1.linear_fc1.bias": "model.safetensors", "visual.deepstack_merger_list.1.linear_fc1.weight": "model.safetensors", "visual.deepstack_merger_list.1.linear_fc1.weight_scale": "model.safetensors", "visual.deepstack_merger_list.1.linear_fc2.bias": "model.safetensors", "visual.deepstack_merger_list.1.linear_fc2.weight": "model.safetensors", "visual.deepstack_merger_list.1.linear_fc2.weight_scale": "model.safetensors", "visual.deepstack_merger_list.1.norm.bias": "model.safetensors", "visual.deepstack_merger_list.1.norm.weight": "model.safetensors", "visual.deepstack_merger_list.2.linear_fc1.bias": "model.safetensors", "visual.deepstack_merger_list.2.linear_fc1.weight": "model.safetensors", "visual.deepstack_merger_list.2.linear_fc1.weight_scale": "model.safetensors", "visual.deepstack_merger_list.2.linear_fc2.bias": "model.safetensors", "visual.deepstack_merger_list.2.linear_fc2.weight": "model.safetensors", "visual.deepstack_merger_list.2.linear_fc2.weight_scale": "model.safetensors", "visual.deepstack_merger_list.2.norm.bias": "model.safetensors", "visual.deepstack_merger_list.2.norm.weight": "model.safetensors", "visual.merger.linear_fc1.bias": "model.safetensors", "visual.merger.linear_fc1.weight": "model.safetensors", "visual.merger.linear_fc1.weight_scale": "model.safetensors", "visual.merger.linear_fc2.bias": "model.safetensors", "visual.merger.linear_fc2.weight": "model.safetensors", "visual.merger.linear_fc2.weight_scale": "model.safetensors", "visual.merger.norm.bias": "model.safetensors", "visual.merger.norm.weight": "model.safetensors", "visual.patch_embed.proj.bias": "model.safetensors", "visual.patch_embed.proj.weight": "model.safetensors", "visual.pos_embed.weight": "model.safetensors"}}

Qwen-3-VL/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

Qwen-3-VL/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}