{"_id":"6a8d07bf3d36bac64fddc09a","id":"tencent/WeMM-Embedding-9B","private":false,"pipeline_tag":"feature-extraction","library_name":"transformers","tags":["transformers","safetensors","qwen3_5","image-text-to-text","sentence-transformers","multimodal-embedding","text-embedding","image-embedding","video-embedding","mrl","feature-extraction","custom_code","zh","en","arxiv:2608.24053","base_model:Qwen/Qwen3.5-9B","base_model:finetune:Qwen/Qwen3.5-9B","license:other","endpoints_compatible","region:us"],"downloads":4063,"likes":120,"modelId":"tencent/WeMM-Embedding-9B","author":"tencent","sha":"00c52839de57a6d4fd5b78cf5522ccf0ac8ea482","lastModified":"2026-09-03T12:23:55.000Z","gated":false,"disabled":false,"model-index":null,"config":{"architectures":["Qwen3_5ForConditionalGeneration"],"model_type":"qwen3_5","auto_map":{"AutoModel":"modeling_wemm_embedding.WeMMEmbedding","AutoModelForCausalLM":"modeling_wemm_embedding.WeMMEmbedding"},"tokenizer_config":{"bos_token":null,"eos_token":"<|endoftext|>","pad_token":"<|endoftext|>","unk_token":null},"chat_template_jinja":"{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\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                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\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{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\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    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\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        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is true %}\n        {{- '<think>\\n' }}\n    {%- else %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}","additional_chat_templates":{"sentence_transformers":"{#- Embedding template used by Sentence Transformers.\n\n    Renders the same surface form as chat_template.jinja for text and images. Video\n    is the exception: it renders as a bare <|video_pad|>, because the processor\n    expands that token into one <seconds><|vision_start|>...<|vision_end|> block per\n    frame and, from transformers 5.3, no longer consumes a surrounding pair. The\n    wrapped form therefore gains a second, unwanted pair of vision boundaries there.\n    This matches embedding_chat_template.jinja, which is bare for the same reason.\n\n    The tokenizer normalizer drops the role newline before a leading image and the\n    newline after the final <|im_end|>, then the post-processor appends <embedding>. #}\n{%- for message in messages %}\n{{- '<|im_start|>' + message.role + '\\n' }}\n{%- if message.content is string %}\n{{- message.content }}\n{%- elif message.content is iterable and message.content is not mapping %}\n{%- for item in message.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 item.type == 'video' %}\n{{- '<|video_pad|>' }}\n{%- elif 'text' in item %}\n{{- item.text }}\n{%- else %}\n{{- raise_exception('Unexpected item type in content.') }}\n{%- endif %}\n{%- endfor %}\n{%- elif message.content is not none %}\n{{- raise_exception('Unexpected content type.') }}\n{%- endif %}\n{{- '<|im_end|>\\n' }}\n{%- endfor %}\n"}},"cardData":{"library_name":"transformers","license":"other","license_name":"apache-2.0","license_link":"https://huggingface.co/tencent/WeMM-Embedding-9B/blob/main/LICENSE","base_model":["Qwen/Qwen3.5-9B"],"pipeline_tag":"feature-extraction","tags":["sentence-transformers","multimodal-embedding","text-embedding","image-embedding","video-embedding","mrl"],"language":["zh","en"]},"transformersInfo":{"auto_model":"AutoModelForMultimodalLM","pipeline_tag":"image-text-to-text","processor":"AutoProcessor"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"LICENSE"},{"rfilename":"README.md"},{"rfilename":"additional_chat_templates/sentence_transformers.jinja"},{"rfilename":"chat_template.jinja"},{"rfilename":"config.json"},{"rfilename":"config_sentence_transformers.json"},{"rfilename":"embedding_chat_template.jinja"},{"rfilename":"model.safetensors"},{"rfilename":"modeling_st_wemm.py"},{"rfilename":"modeling_wemm_embedding.py"},{"rfilename":"modules.json"},{"rfilename":"patch_sglang_video.py"},{"rfilename":"processor_config.json"},{"rfilename":"sentence_bert_config.json"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"}],"spaces":["Mike0021/WeMM-Embedding-9B"],"createdAt":"2026-08-25T03:10:55.000Z","safetensors":{"parameters":{"BF16":9407831280},"total":9407831280},"usedStorage":18835747836}