Delete QeoThinker-VGGT-Qwen3VL-8B-Scaled

QeoThinker-VGGT-Qwen3VL-8B-Scaled/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
-}

QeoThinker-VGGT-Qwen3VL-8B-Scaled/chat_template.json

@@ -1,3 +0,0 @@
-{
-    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
-}

QeoThinker-VGGT-Qwen3VL-8B-Scaled/config.json

@@ -1,91 +0,0 @@
-{
-  "align_method": "zero",
-  "align_method_weight": 0.1,
-  "architectures": [
-    "Qwen3VLForConditionalGenerationWithVGGT"
-  ],
-  "cam_merger_type": "zero",
-  "depart_smi_token": true,
-  "dtype": "bfloat16",
-  "eos_token_id": 151645,
-  "feature_fusion_method": "zero",
-  "fusion_num_layers": 1,
-  "geometry_encoder_type": "vggt",
-  "geometry_merger_type": "mlp",
-  "image_token_id": 151655,
-  "model_type": "qwen3_vl",
-  "pad_token_id": 151643,
-  "reference_frame": "first",
-  "selection_method": "zero",
-  "selection_method_ratio": 0.25,
-  "smi_downsample_rate": 2,
-  "smi_image_num": 8,
-  "text_config": {
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "bos_token_id": 151643,
-    "depart_smi_token": true,
-    "dtype": "bfloat16",
-    "eos_token_id": 151645,
-    "geo_cross_attn": true,
-    "geo_importance_gate": true,
-    "geo_inject_version": "v2_flash",
-    "geo_layer_interval": 1,
-    "geo_learn_bias": false,
-    "geo_spatial_bias": false,
-    "head_dim": 128,
-    "hidden_act": "silu",
-    "hidden_size": 4096,
-    "initializer_range": 0.02,
-    "intermediate_size": 12288,
-    "max_position_embeddings": 262144,
-    "model_type": "qwen3_vl_text",
-    "num_attention_heads": 32,
-    "num_hidden_layers": 36,
-    "num_key_value_heads": 8,
-    "rms_norm_eps": 1e-06,
-    "rope_scaling": {
-      "mrope_interleaved": true,
-      "mrope_section": [
-        24,
-        20,
-        20
-      ],
-      "rope_type": "default"
-    },
-    "rope_theta": 5000000,
-    "smi_downsample_rate": 2,
-    "smi_image_num": 8,
-    "use_cache": true,
-    "vocab_size": 151936
-  },
-  "tie_word_embeddings": false,
-  "training": true,
-  "transformers_version": "4.57.0",
-  "use_cache": true,
-  "use_geometry_encoder": true,
-  "video_token_id": 151656,
-  "vision_config": {
-    "deepstack_visual_indexes": [
-      8,
-      16,
-      24
-    ],
-    "depth": 27,
-    "dtype": "bfloat16",
-    "hidden_act": "gelu_pytorch_tanh",
-    "hidden_size": 1152,
-    "in_channels": 3,
-    "initializer_range": 0.02,
-    "intermediate_size": 4304,
-    "model_type": "qwen3_vl",
-    "num_heads": 16,
-    "num_position_embeddings": 2304,
-    "out_hidden_size": 4096,
-    "patch_size": 16,
-    "spatial_merge_size": 2,
-    "temporal_patch_size": 2
-  },
-  "vision_end_token_id": 151653,
-  "vision_start_token_id": 151652
-}

QeoThinker-VGGT-Qwen3VL-8B-Scaled/generation_config.json

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

QeoThinker-VGGT-Qwen3VL-8B-Scaled/model-00001-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6ee714633d25cbcdb0f832c7652f2c36d18ef84219b046667a5734466719d26c
-size 4979465244

QeoThinker-VGGT-Qwen3VL-8B-Scaled/model-00002-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:031558241d4570d6f1bb2474f901cbbc0178308f83be5980a971d4d00f4a82a3
-size 4959362212

QeoThinker-VGGT-Qwen3VL-8B-Scaled/model-00003-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:00b88c7f1a43b578fcb3d42f194111118c6d46dcf17a1ee5c3d702ed13756876
-size 4992967326

QeoThinker-VGGT-Qwen3VL-8B-Scaled/model-00004-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b0cc6ae4dbeec5d65a937b0cc2ad28bc5814ff153ffe8f9cd4cc4a887251fb84
-size 4951110990

QeoThinker-VGGT-Qwen3VL-8B-Scaled/model-00005-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ebec8be623dbd60bb5405926b0706495edd353a33a47fba9905ebc803efeab6d
-size 4760811764

QeoThinker-VGGT-Qwen3VL-8B-Scaled/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": 451584,
-  "merge_size": 2,
-  "min_pixels": 12544,
-  "pad_size": null,
-  "patch_size": 16,
-  "processor_class": "Qwen3VLProcessor",
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "return_tensors": null,
-  "size": {
-    "longest_edge": 451584,
-    "shortest_edge": 12544
-  },
-  "temporal_patch_size": 2
-}

QeoThinker-VGGT-Qwen3VL-8B-Scaled/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
-  }
-}

QeoThinker-VGGT-Qwen3VL-8B-Scaled/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": 12800,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}

QeoThinker-VGGT-Qwen3VL-8B-Scaled/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:379735ed2e8bf214c945b99811b0c6ef43075b68f5b4b5094b4e6d4f04ac4b7e
-size 7480