Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,110 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- else %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                <|vision_start|><|image_pad|><|vision_end|>
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                <|vision_start|><|video_pad|><|vision_end|>
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{%- endmacro %}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- render_content(messages[0].content, false) + '\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' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false) %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, True) %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and 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' }}
+        {{- content }}
+        {{- '\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<think>\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3VLMoeForConditionalGeneration"
+  ],
+  "eos_token_id": 151645,
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl_moe",
+  "pad_token_id": 151643,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "decoder_sparse_step": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_vl_moe_text",
+    "moe_intermediate_size": 768,
+    "norm_topk_prob": true,
+    "num_attention_heads": 32,
+    "num_experts": 128,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 4,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "router_aux_loss_coef": 0.001,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl_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": 151653,
+  "vision_start_token_id": 151652
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.8,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.0.dev0"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1165fcf0f1cfb9b6f4b235e90dde91a17352b98ea3f4ffcffd09d4667a101c
+size 4399341000

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299d234d5a9e2a750bc3e0fdcb4fe07fd45c17d403d22ee9d51355d07ba2a7a
+size 4984970848

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f2b0fa3e6ee6694dd01f5d42ec12b74b8e2e18bc23cb963137e34ee46c064c
+size 4984970856

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c19d4b469f01c3a020e168a4286f2c91940e50e89b84531431986ae5bb1bead7
+size 4984970896

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc0e7d5bc8582104eec23f5450ff53a43027a02329d3592040ed00a9cef09c1c
+size 4984970896

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df60f43c89b41cf8c8a9d6c07c78b815ca6b1797bbc980aecd4181128f6b8353
+size 4984970896

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3640d84fce835f9b3a4e8900d7341538bb5331a511b147b3d833edd97e4c91
+size 4984970896

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f96381047414778e0ca791e5e4908302305a505b4957a91e9d2a19bdba58419d
+size 4984970896

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6920a590609e662003072ed9156392b0e053c8a76a6a18521611f550e654a6f
+size 4984970896

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c122a50f4d07d2cd8c60d21610655a36d079e634757c5cf33b776f9df766ba
+size 4984970896

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed80c17ec5e86093ff3980c50bed2b90dd0172a1a53eb171f522057ec3eaa861
+size 4984970896

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a0a0e3c394ad7b15b48eddf2a4bcc8fe2b64c32443ddf0081766ab7db63c7a9
+size 4984970896

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810f76ab5e66426f2e41fbbfe9bc535486f7cfd99c94b882c45154456719f279
+size 2907596832

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 62141508064}, "weight_map": {"lm_head.weight": "model-00013-of-00013.safetensors", "model.language_model.embed_tokens.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.0.mlp.experts.down_proj": "model-00001-of-00013.safetensors", "model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors", "model.language_model.layers.0.mlp.gate.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.1.mlp.experts.down_proj": "model-00001-of-00013.safetensors", "model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors", "model.language_model.layers.1.mlp.gate.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.10.mlp.experts.down_proj": "model-00003-of-00013.safetensors", "model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", "model.language_model.layers.10.mlp.gate.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.10.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.10.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.10.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.11.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.11.mlp.experts.down_proj": "model-00004-of-00013.safetensors", "model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", "model.language_model.layers.11.mlp.gate.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.11.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.11.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.11.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.11.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.11.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.11.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.11.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.12.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.12.mlp.experts.down_proj": "model-00004-of-00013.safetensors", "model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", "model.language_model.layers.12.mlp.gate.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.12.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.12.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.12.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.13.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.13.mlp.experts.down_proj": "model-00004-of-00013.safetensors", "model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", "model.language_model.layers.13.mlp.gate.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.13.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.13.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.13.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.13.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.13.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.13.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.14.mlp.experts.down_proj": "model-00004-of-00013.safetensors", "model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", "model.language_model.layers.14.mlp.gate.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.14.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.14.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.15.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.15.mlp.experts.down_proj": "model-00005-of-00013.safetensors", "model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", "model.language_model.layers.15.mlp.gate.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.15.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.15.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.language_model.layers.16.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.16.mlp.experts.down_proj": "model-00005-of-00013.safetensors", "model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", "model.language_model.layers.16.mlp.gate.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.16.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.16.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.16.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.16.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.16.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.16.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.16.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.17.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.17.mlp.experts.down_proj": "model-00005-of-00013.safetensors", "model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", "model.language_model.layers.17.mlp.gate.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.17.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.17.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.17.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.17.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.17.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.17.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.17.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.18.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.18.mlp.experts.down_proj": "model-00005-of-00013.safetensors", "model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", "model.language_model.layers.18.mlp.gate.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.18.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.18.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.18.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.18.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.18.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.18.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.18.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.19.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.19.mlp.experts.down_proj": "model-00006-of-00013.safetensors", "model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", "model.language_model.layers.19.mlp.gate.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.19.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.19.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.19.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.19.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.19.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.19.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.19.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.2.mlp.experts.down_proj": "model-00001-of-00013.safetensors", "model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors", "model.language_model.layers.2.mlp.gate.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.20.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.20.mlp.experts.down_proj": "model-00006-of-00013.safetensors", "model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", "model.language_model.layers.20.mlp.gate.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.20.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.20.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.20.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.20.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.20.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.20.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.20.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.21.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.21.mlp.experts.down_proj": "model-00006-of-00013.safetensors", "model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", "model.language_model.layers.21.mlp.gate.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.21.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.21.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.21.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.21.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.21.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.21.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.21.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.22.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.22.mlp.experts.down_proj": "model-00006-of-00013.safetensors", "model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", "model.language_model.layers.22.mlp.gate.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.22.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.22.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.22.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.22.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.22.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.22.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.22.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.23.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.23.mlp.experts.down_proj": "model-00007-of-00013.safetensors", "model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", "model.language_model.layers.23.mlp.gate.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.23.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.23.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.23.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.23.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.23.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.23.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.23.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.language_model.layers.24.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.24.mlp.experts.down_proj": "model-00007-of-00013.safetensors", "model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", "model.language_model.layers.24.mlp.gate.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.24.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.24.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.24.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.24.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.24.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.24.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.24.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.25.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.25.mlp.experts.down_proj": "model-00007-of-00013.safetensors", "model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", "model.language_model.layers.25.mlp.gate.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.25.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.25.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.25.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.25.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.25.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.25.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.25.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.26.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.26.mlp.experts.down_proj": "model-00007-of-00013.safetensors", "model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", "model.language_model.layers.26.mlp.gate.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.26.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.26.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.26.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.26.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.26.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.26.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.26.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.27.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.27.mlp.experts.down_proj": "model-00008-of-00013.safetensors", "model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", "model.language_model.layers.27.mlp.gate.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.27.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.27.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.27.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.27.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.27.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.27.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.27.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.language_model.layers.28.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.28.mlp.experts.down_proj": "model-00008-of-00013.safetensors", "model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", "model.language_model.layers.28.mlp.gate.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.28.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.28.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.28.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.28.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.28.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.28.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.28.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.29.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.29.mlp.experts.down_proj": "model-00008-of-00013.safetensors", "model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", "model.language_model.layers.29.mlp.gate.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.29.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.29.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.29.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.29.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.29.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.29.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.29.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.3.mlp.experts.down_proj": "model-00002-of-00013.safetensors", "model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", "model.language_model.layers.3.mlp.gate.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.language_model.layers.30.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.30.mlp.experts.down_proj": "model-00008-of-00013.safetensors", "model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", "model.language_model.layers.30.mlp.gate.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.30.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.30.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.30.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.30.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.30.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.30.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.30.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.31.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.31.mlp.experts.down_proj": "model-00009-of-00013.safetensors", "model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", "model.language_model.layers.31.mlp.gate.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.31.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.31.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.31.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.31.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.31.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.31.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.31.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.language_model.layers.32.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.32.mlp.experts.down_proj": "model-00009-of-00013.safetensors", "model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", "model.language_model.layers.32.mlp.gate.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.32.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.32.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.32.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.32.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.32.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.32.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.32.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.33.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.33.mlp.experts.down_proj": "model-00009-of-00013.safetensors", "model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", "model.language_model.layers.33.mlp.gate.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.33.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.33.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.33.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.33.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.33.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.33.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.33.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.34.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.34.mlp.experts.down_proj": "model-00009-of-00013.safetensors", "model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", "model.language_model.layers.34.mlp.gate.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.34.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.34.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.34.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.34.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.34.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.34.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.34.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.35.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.35.mlp.experts.down_proj": "model-00010-of-00013.safetensors", "model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", "model.language_model.layers.35.mlp.gate.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.35.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.35.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.35.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.35.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.35.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.35.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.35.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.language_model.layers.36.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.36.mlp.experts.down_proj": "model-00010-of-00013.safetensors", "model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", "model.language_model.layers.36.mlp.gate.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.36.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.36.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.36.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.36.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.36.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.36.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.36.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.37.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.37.mlp.experts.down_proj": "model-00010-of-00013.safetensors", "model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", "model.language_model.layers.37.mlp.gate.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.37.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.37.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.37.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.37.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.37.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.37.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.37.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.38.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.38.mlp.experts.down_proj": "model-00010-of-00013.safetensors", "model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", "model.language_model.layers.38.mlp.gate.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.38.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.38.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.38.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.38.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.38.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.38.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.38.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.39.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.39.mlp.experts.down_proj": "model-00011-of-00013.safetensors", "model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", "model.language_model.layers.39.mlp.gate.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.39.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.39.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.39.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.39.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.39.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.39.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.39.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.4.mlp.experts.down_proj": "model-00002-of-00013.safetensors", "model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", "model.language_model.layers.4.mlp.gate.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.40.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.40.mlp.experts.down_proj": "model-00011-of-00013.safetensors", "model.language_model.layers.40.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", "model.language_model.layers.40.mlp.gate.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.40.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.40.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.40.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.40.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.40.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.40.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.40.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.41.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.41.mlp.experts.down_proj": "model-00011-of-00013.safetensors", "model.language_model.layers.41.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", "model.language_model.layers.41.mlp.gate.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.41.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.41.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.41.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.41.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.41.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.41.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.41.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.42.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.42.mlp.experts.down_proj": "model-00011-of-00013.safetensors", "model.language_model.layers.42.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", "model.language_model.layers.42.mlp.gate.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.42.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.42.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.42.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.42.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.42.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.42.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.42.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.43.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.43.mlp.experts.down_proj": "model-00012-of-00013.safetensors", "model.language_model.layers.43.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", "model.language_model.layers.43.mlp.gate.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.43.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.43.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.43.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.43.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.43.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.43.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.43.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.language_model.layers.44.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.44.mlp.experts.down_proj": "model-00012-of-00013.safetensors", "model.language_model.layers.44.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", "model.language_model.layers.44.mlp.gate.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.44.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.44.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.44.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.44.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.44.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.44.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.44.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.45.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.45.mlp.experts.down_proj": "model-00012-of-00013.safetensors", "model.language_model.layers.45.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", "model.language_model.layers.45.mlp.gate.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.45.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.45.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.45.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.45.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.45.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.45.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.45.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.46.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.46.mlp.experts.down_proj": "model-00012-of-00013.safetensors", "model.language_model.layers.46.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", "model.language_model.layers.46.mlp.gate.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.46.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.46.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.46.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.46.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.46.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.46.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.46.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.47.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.47.mlp.experts.down_proj": "model-00013-of-00013.safetensors", "model.language_model.layers.47.mlp.experts.gate_up_proj": "model-00013-of-00013.safetensors", "model.language_model.layers.47.mlp.gate.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.47.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.47.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.47.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.47.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.47.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.47.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.47.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.5.mlp.experts.down_proj": "model-00002-of-00013.safetensors", "model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", "model.language_model.layers.5.mlp.gate.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.6.mlp.experts.down_proj": "model-00002-of-00013.safetensors", "model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", "model.language_model.layers.6.mlp.gate.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.7.mlp.experts.down_proj": "model-00003-of-00013.safetensors", "model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", "model.language_model.layers.7.mlp.gate.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.language_model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.8.mlp.experts.down_proj": "model-00003-of-00013.safetensors", "model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", "model.language_model.layers.8.mlp.gate.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.8.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.8.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.9.mlp.experts.down_proj": "model-00003-of-00013.safetensors", "model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", "model.language_model.layers.9.mlp.gate.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.9.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.9.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.language_model.norm.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.0.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.0.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.0.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.0.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.0.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.0.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.0.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.0.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.1.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.1.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.1.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.1.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.1.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.1.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.1.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.1.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.10.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.10.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.10.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.10.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.10.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.10.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.10.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.10.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.11.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.11.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.11.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.11.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.11.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.11.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.11.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.11.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.12.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.12.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.12.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.12.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.12.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.12.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.12.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.12.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.13.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.13.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.13.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.13.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.13.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.13.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.13.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.13.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.14.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.14.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.14.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.14.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.14.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.14.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.14.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.14.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.15.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.15.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.15.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.15.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.15.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.15.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.15.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.15.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.16.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.16.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.16.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.16.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.16.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.16.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.16.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.16.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.17.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.17.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.17.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.17.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.17.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.17.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.17.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.17.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.18.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.18.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.18.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.18.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.18.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.18.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.18.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.18.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.19.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.19.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.19.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.19.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.19.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.19.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.19.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.19.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.2.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.2.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.2.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.2.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.2.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.2.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.2.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.2.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.20.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.20.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.20.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.20.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.20.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.20.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.20.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.20.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.21.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.21.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.21.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.21.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.21.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.21.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.21.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.21.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.22.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.22.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.22.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.22.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.22.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.22.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.22.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.22.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.23.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.23.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.23.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.23.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.23.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.23.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.23.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.23.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.24.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.24.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.24.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.24.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.24.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.24.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.24.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.24.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.25.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.25.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.25.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.25.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.25.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.25.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.25.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.25.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.26.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.26.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.26.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.26.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.26.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.26.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.26.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.26.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.3.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.3.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.3.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.3.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.3.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.3.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.3.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.3.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.4.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.4.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.4.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.4.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.4.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.4.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.4.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.4.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.5.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.5.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.5.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.5.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.5.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.5.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.5.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.5.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.6.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.6.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.6.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.6.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.6.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.6.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.6.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.6.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.7.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.7.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.7.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.7.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.7.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.7.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.7.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.7.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.8.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.8.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.8.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.8.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.8.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.8.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.8.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.8.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.9.attn.proj.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.9.attn.proj.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.9.attn.qkv.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.9.attn.qkv.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.9.norm1.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.9.norm1.weight": "model-00013-of-00013.safetensors", "model.visual.blocks.9.norm2.bias": "model-00013-of-00013.safetensors", "model.visual.blocks.9.norm2.weight": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.0.norm.bias": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.0.norm.weight": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.1.norm.bias": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.1.norm.weight": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.2.norm.bias": "model-00013-of-00013.safetensors", "model.visual.deepstack_merger_list.2.norm.weight": "model-00013-of-00013.safetensors", "model.visual.merger.linear_fc1.bias": "model-00013-of-00013.safetensors", "model.visual.merger.linear_fc1.weight": "model-00013-of-00013.safetensors", "model.visual.merger.linear_fc2.bias": "model-00013-of-00013.safetensors", "model.visual.merger.linear_fc2.weight": "model-00013-of-00013.safetensors", "model.visual.merger.norm.bias": "model-00013-of-00013.safetensors", "model.visual.merger.norm.weight": "model-00013-of-00013.safetensors", "model.visual.patch_embed.proj.bias": "model-00013-of-00013.safetensors", "model.visual.patch_embed.proj.weight": "model-00013-of-00013.safetensors", "model.visual.pos_embed.weight": "model-00013-of-00013.safetensors"}}

preprocessor_config.json

@@ -0,0 +1,38 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_pixels": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}