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

config.json

@@ -0,0 +1,142 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "hidden_size": 5120,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 17408,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 48,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 24,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.12.1",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "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_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 248044,
+  "do_sample": true,
+  "eos_token_id": [
+      248046,
+      248044
+  ],
+  "pad_token_id": 248044,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 0.95
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6360e5971d200cd5dc60a6d9d4960928f513d98481948bad4ef587f40644b766
+size 4997391272

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0860ec6d86d802928da99530888d90c99c1017177f94b813daad158cd72f2d7f
+size 4965238248

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d71e8d416ef8e63e0f3a1c469a8c3b93a946bd26f57b2aff2df35ddb3383aab7
+size 4933779360

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb59ef1dedd0af84056678efa930eba43f3d10d30f1115cec4707d0af8fb3f15
+size 4965238360

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d10dd7c6548ead26e4700a5e6eb7da1bae27e4e671cb112117763270d59b1f
+size 4911743112

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dcf2f503e3c4c7248287a4ba1a6c03b3b2672bac813e2ceb1e480a6f1d9fec1
+size 4987274624

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c0770390e999c024c8aa694e830d502ba86633eb5a6e0ff9bec9654e5350a2
+size 4911743120

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e131fbb57ac42998c67fe1fb193ecf5431355b52a3f493a8e249e34573e9a1e1
+size 4965238320

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c37ac3a98d369a2252fdf84a2f61fdc0a510903ceaa8bdc1de2675909a39954
+size 4933779424

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc36a17231ce920409ba5c92be19f4012f3839a177402c4f0a3f6cc1b966b803
+size 4965238336

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e917065362cc27ab6b2ff763a6b462b109eae6ce286d54c1a2ffa4d0426709
+size 3483535200

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f84c863100eeea9dc052b27c6eb4b0181a4ff7f086933c27922590c640c0d5
+size 2542807248

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "chat_template": "{%- macro render_content(content) -%}\n    {%- if content is string -%}\n        {{- content -}}\n    {%- elif content is iterable and content is not mapping -%}\n        {%- for item in content -%}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' -%}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' -}}\n            {%- elif 'video' in item or 'video_url' in item or item.type == 'video' -%}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' -}}\n            {%- elif 'text' in item -%}\n                {{- item.text -}}\n            {%- else -%}\n                {{- raise_exception('Unexpected item type in content.') -}}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- elif content is none or content is undefined -%}\n        {{- '' -}}\n    {%- else -%}\n        {{- raise_exception('Unexpected content type.') -}}\n    {%- endif -%}\n{%- endmacro -%}\n\n{%- macro render_tool_calls(tool_calls) -%}\n    {%- for tool_call in tool_calls -%}\n        {%- if tool_call.function is defined -%}\n            {%- set tool_call = tool_call.function -%}\n        {%- endif -%}\n        {%- if not loop.first -%}\n            {{- '\\n' -}}\n        {%- endif -%}\n        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' -}}\n        {%- if tool_call.arguments is defined -%}\n            {%- for args_name, args_value in tool_call.arguments|items -%}\n                {{- '<parameter=' + args_name + '>\\n' -}}\n                {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string -%}\n                {{- args_value -}}\n                {{- '\\n</parameter>\\n' -}}\n            {%- endfor -%}\n        {%- endif -%}\n        {{- '</function>\\n</tool_call>' -}}\n    {%- endfor -%}\n{%- endmacro -%}\n\n{%- if enable_thinking is true -%}\n    {%- set final_mode = 'Enable_Thinking' -%}\n{%- else -%}\n    {%- set final_mode = 'Adaptive_Thinking' -%}\n{%- endif -%}\n{%- set mode_state = namespace(last_user_index=-1) -%}\n{%- for candidate in messages -%}\n    {%- if candidate['role'] in ['user','system','developer','tool'] -%}\n        {%- set mode_state.last_user_index = loop.index0 -%}\n    {%- endif -%}\n{%- endfor -%}\n\nA chat between a user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\n{%- set merged = namespace(user='', asst='', last_user_role='', tools_rendered=false) -%}\n{%- for message in messages -%}\n    {%- set raw_role = message['role'] -%}\n    {%- set role = 'user' if raw_role in ['user','system','developer','tool'] else 'assistant' -%}\n    {%- set content = render_content(message['content']) -%}\n    {%- if raw_role == 'tool' -%}\n        {%- set content = '<tool_response>\\n' + (content|trim) + '\\n</tool_response>' -%}\n    {%- elif raw_role == 'assistant' -%}\n        {%- set reasoning = message.get('reasoning') -%}\n        {%- if reasoning is none -%}\n            {%- set reasoning = message.get('reasoning_content') -%}\n        {%- endif -%}\n        {%- if reasoning is not none -%}\n            {%- set content = '<think>' + reasoning + '</think>' + content -%}\n        {%- elif content[:7] != '<think>' -%}\n            {%- if '</think>' in content -%}\n                {%- set content = '<think>' + content -%}\n            {%- else -%}\n                {%- set content = '<think>\\n\\n</think>\\n\\n' + content -%}\n            {%- endif -%}\n        {%- endif -%}\n        {%- if message.get('tool_calls') and message['tool_calls'] is iterable and message['tool_calls'] is not mapping -%}\n            {%- set tool_calls_content = render_tool_calls(message['tool_calls']) -%}\n            {%- set content = content|trim -%}\n            {%- set content = content + ('\\n\\n' if content else '') + tool_calls_content -%}\n        {%- endif -%}\n    {%- endif -%}\n\n    {%- if role == 'user' -%}\n        {%- if raw_role == 'tool' and merged.last_user_role == 'tool' -%}\n            {%- set merged.user = merged.user + '\\n' + content -%}\n        {%- else -%}\n            {%- set merged.user = merged.user + ('\\n\\n' if merged.user else '') + content -%}\n        {%- endif -%}\n        {%- set merged.last_user_role = raw_role -%}\n    {%- else -%}\n        {%- set merged.asst = merged.asst + ('\\n\\n' if merged.asst else '') + content -%}\n    {%- endif -%}\n\n    {%- set next_role = role -%}\n    {%- if not loop.last -%}\n        {%- set next_raw = messages[loop.index0+1]['role'] -%}\n        {%- set next_role = 'user' if next_raw in ['user','system','developer','tool'] else 'assistant' -%}\n    {%- endif -%}\n\n    {%- if loop.last or next_role != role -%}\n        {%- if role == 'user' -%}\n            {%- set is_last_user = loop.index0 == mode_state.last_user_index -%}\n            {%- set mode = final_mode if is_last_user else 'Adaptive_Thinking' -%}\n            {{- '\\n<|User|>\\n' -}}\n            {%- if tools and tools is iterable and tools is not mapping and not merged.tools_rendered -%}\n                {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" -}}\n                {%- for tool in tools -%}\n                    {{- \"\\n\" -}}\n                    {{- tool | tojson -}}\n                {%- endfor -%}\n                {{- \"\\n</tools>\" -}}\n                {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>\\n\\n' -}}\n                {%- set merged.tools_rendered = true -%}\n            {%- endif -%}\n            {{- merged.user + '\\n/' + mode + '\\n<|Assistant|>\\n' -}}\n            {%- if loop.last -%}\n                {{- '<think>' -}}\n            {%- endif -%}\n            {%- set merged.user = '' -%}\n            {%- set merged.last_user_role = '' -%}\n        {%- else -%}\n            {{- merged.asst + '<|endoftext|>' -}}\n            {%- set merged.asst = '' -%}\n        {%- endif -%}\n    {%- endif -%}\n{%- endfor -%}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}