Delete 30000

30000/adapters/transformer/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:df8c7e99d2a4db785df1ab4e6448b0e6f001fbbad08c3ddae438a933591ffcd4
-size 88553624

30000/assets/norm_stats.json

@@ -1,154 +0,0 @@
-{
-  "norm_stats": {
-    "state": {
-      "count": 273408,
-      "mean": [
-        -0.046515832679548515,
-        0.03437810533502129,
-        0.7644975640800562,
-        2.9721761982092696,
-        -0.2203380713302098,
-        -0.12565075592155314,
-        0.026918238021907737,
-        -0.02719479107231683,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0
-      ],
-      "std": [
-        0.1049430405120553,
-        0.15176749532203646,
-        0.37853701762601316,
-        0.34430596099033595,
-        0.9069933264633429,
-        0.32538961158764335,
-        0.014174073074704035,
-        0.01405701171059929,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0
-      ],
-      "q01": [
-        -0.39929718182235957,
-        -0.2688781352341175,
-        0.0380015922319144,
-        1.5076640663146972,
-        -2.7231650549173354,
-        -1.082290536224842,
-        0.0017220906309667046,
-        -0.04006594421766931,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0
-      ],
-      "q99": [
-        0.13511216131597759,
-        0.3353764298558235,
-        1.2689219574783928,
-        3.2748465917110443,
-        2.40471659219265,
-        0.5968299900889398,
-        0.040285861361655406,
-        -0.0018051995920250197,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0
-      ]
-    },
-    "actions": {
-      "count": 273408,
-      "mean": [
-        0.06270760811223519,
-        0.0868575278292881,
-        -0.09040560347310612,
-        0.0005443644769182812,
-        0.00564395800958412,
-        -0.005221108818768562,
-        0.0,
-        0.5248822272940075,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0
-      ],
-      "std": [
-        0.33547515422916885,
-        0.37848309424500604,
-        0.44467916095569604,
-        0.039240949042962214,
-        0.06338541435693439,
-        0.07797358906933648,
-        0.0,
-        0.4993804909734554,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0
-      ],
-      "q01": [
-        -0.7050000000000001,
-        -0.8015625,
-        -0.9375,
-        -0.11486197002232074,
-        -0.16425,
-        -0.22419750577211378,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0
-      ],
-      "q99": [
-        0.9365625,
-        0.8671875,
-        0.9365625,
-        0.13070946447551252,
-        0.19274999999999998,
-        0.33490499961376197,
-        0.0,
-        0.9995,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0,
-        0.0
-      ]
-    }
-  }
-}

30000/config.json

@@ -1,17 +0,0 @@
-{
-  "_class_name": "QWenVLA",
-  "_diffusers_version": "0.35.1",
-  "_load_submodules": true,
-  "action_dim": 16,
-  "action_horizon": 30,
-  "dit_variant": "mmflow-base",
-  "img_vae_variant": "qwen-image",
-  "max_views": 3,
-  "patch_size": 2,
-  "strength": 1.0,
-  "use_goal_image": true,
-  "use_primary_goal_image_only": true,
-  "vlm_load_in_4bit": true,
-  "vlm_load_in_8bit": false,
-  "vlm_variant": "qwen3-vl-4b"
-}

30000/img_vae/config.json

@@ -1,16 +0,0 @@
-{
-  "architectures": [
-    "HuggingFaceVAE"
-  ],
-  "device_map": "auto",
-  "dtype": "bfloat16",
-  "freeze": true,
-  "latent_channels": 16,
-  "model_dtype": "bfloat16",
-  "model_type": "vision_vae",
-  "name": "Qwen/Qwen-Image",
-  "patch_size": 8,
-  "transformers_version": "4.57.0",
-  "trust_remote_code": true,
-  "vae_type": "autoencoder_kl"
-}

30000/img_vae/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f9646c3092eed46c221c1e11c3e6c58e4f8860f93f467f95b6f64fc1c4629524
-size 253807742

30000/metadata.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5d70d4e8d01e7af2f678d643b201eab488c978caa963544c1a4f53b027cd7c24
-size 3699

30000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06cafafd66948a0496c2e41dda78eac9ebd490a080d8310c449f8e305285006e
-size 175280599

30000/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a78ceaa66f62910fbe9ac23e14b4075d560f243758249984b2212d7031cca631
-size 1401

30000/transformer/config.json

@@ -1,29 +0,0 @@
-{
-  "action_dim": 16,
-  "action_horizon": 30,
-  "architectures": [
-    "MMFlowTransformer"
-  ],
-  "condition_dim": 768,
-  "dim_head": 64,
-  "dtype": "float32",
-  "embed_dim": 768,
-  "ff_kwargs": {
-    "hidden_features": 3072
-  },
-  "img_vae_patch_size": 8,
-  "in_channels": 16,
-  "max_views": 3,
-  "model_type": "mmflow_transformer",
-  "name": "mmflow-base",
-  "num_blocks": 28,
-  "num_heads": 12,
-  "num_modalities": 4,
-  "out_channels": 16,
-  "patch_size": 2,
-  "qk_rmsnorm": true,
-  "transformers_version": "4.57.0",
-  "use_goal_image": true,
-  "use_primary_goal_image_only": true,
-  "vlm_dim": 2560
-}

30000/transformer/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f5c2b1f50fc3b3dbdac4af403bd4110079b9ded6bccdb852f3154b9e44d468f6
-size 4870539088

30000/vlm/config.json

@@ -1,22 +0,0 @@
-{
-  "architectures": [
-    "VLM"
-  ],
-  "attn_implementation": "sdpa",
-  "bnb_4bit_compute_dtype": "bfloat16",
-  "device_map": "cuda",
-  "dtype": "bfloat16",
-  "hidden_size": 2560,
-  "load_in_4bit": true,
-  "load_in_8bit": false,
-  "max_new_tokens": 1024,
-  "max_tokens": 300,
-  "model_dtype": "bfloat16",
-  "model_id": "Qwen/Qwen3-VL-4B-Instruct",
-  "model_type": "vlm",
-  "system_prompt": "\nYou're a robot visual perception module for robot manipulation.\n\n## Inputs:\n<image_1>: head camera (primary view)\n<image_2>: left wrist camera, valid only if left_cam_present = true\n<image_3>: right wrist camera, valid only if right_cam_present = true\n\n## Rules:\n- Ignore any wrist image whose present flag is false.\n- Do not infer information from missing cameras.\n- Base all understanding on visible evidence only.\n\n## Objective:\nEncode objects, spatial relations, and manipulation-relevant affordances.\n",
-  "transformers_version": "4.57.0",
-  "trust_remote_code": true,
-  "use_double_quant": false,
-  "use_nf4": false
-}

30000/vlm/inner_model/added_tokens.json

@@ -1,28 +0,0 @@
-{
-  "</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
-}

30000/vlm/inner_model/chat_template.jinja

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

30000/vlm/inner_model/config.json

@@ -1,80 +0,0 @@
-{
-  "architectures": [
-    "Qwen3VLForConditionalGeneration"
-  ],
-  "dtype": "bfloat16",
-  "image_token_id": 151655,
-  "model_type": "qwen3_vl",
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
-  "text_config": {
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "bos_token_id": 151643,
-    "dtype": "bfloat16",
-    "eos_token_id": 151645,
-    "head_dim": 128,
-    "hidden_act": "silu",
-    "hidden_size": 2560,
-    "initializer_range": 0.02,
-    "intermediate_size": 9728,
-    "max_position_embeddings": 262144,
-    "model_type": "qwen3_vl_text",
-    "num_attention_heads": 32,
-    "num_hidden_layers": 36,
-    "num_key_value_heads": 8,
-    "rms_norm_eps": 1e-06,
-    "rope_scaling": {
-      "mrope_interleaved": true,
-      "mrope_section": [
-        24,
-        20,
-        20
-      ],
-      "rope_type": "default"
-    },
-    "rope_theta": 5000000,
-    "tie_word_embeddings": true,
-    "use_cache": true,
-    "vocab_size": 151936
-  },
-  "tie_word_embeddings": true,
-  "transformers_version": "4.57.0",
-  "video_token_id": 151656,
-  "vision_config": {
-    "deepstack_visual_indexes": [
-      5,
-      11,
-      17
-    ],
-    "depth": 24,
-    "dtype": "bfloat16",
-    "hidden_act": "gelu_pytorch_tanh",
-    "hidden_size": 1024,
-    "in_channels": 3,
-    "initializer_range": 0.02,
-    "intermediate_size": 4096,
-    "model_type": "qwen3_vl",
-    "num_heads": 16,
-    "num_position_embeddings": 2304,
-    "out_hidden_size": 2560,
-    "patch_size": 16,
-    "spatial_merge_size": 2,
-    "temporal_patch_size": 2
-  },
-  "vision_end_token_id": 151653,
-  "vision_start_token_id": 151652
-}

30000/vlm/inner_model/generation_config.json

@@ -1,13 +0,0 @@
-{
-  "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
-  "transformers_version": "4.57.0"
-}

30000/vlm/inner_model/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5d2f77bc5423bd80ad85880cf6e259928e9e69ef71953460ad767b31092ab09e
-size 3062596856

30000/vlm/inner_model/preprocessor_config.json

@@ -1,39 +0,0 @@
-{
-  "crop_size": null,
-  "data_format": "channels_first",
-  "default_to_square": true,
-  "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
-}

30000/vlm/inner_model/special_tokens_map.json

@@ -1,31 +0,0 @@
-{
-  "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
-  }
-}

30000/vlm/inner_model/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ffef306165070c2b77d0fc1a4ff3981511a8049b13e6fb91b0f6613ec5ab7d01
-size 11422932

30000/vlm/inner_model/tokenizer_config.json

@@ -1,240 +0,0 @@
-{
-  "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
-}

30000/vlm/inner_model/video_preprocessor_config.json

@@ -1,41 +0,0 @@
-{
-  "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_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,
-  "size": {
-    "longest_edge": 25165824,
-    "shortest_edge": 4096
-  },
-  "temporal_patch_size": 2,
-  "video_metadata": null,
-  "video_processor_type": "Qwen3VLVideoProcessor"
-}

30000/vlm/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:57df2f63d620a6e211732eb7dee3a178cc53223bba29b690935a6d47ec50fb2f
-size 3062607544