{"_id":"678dc6fff905d106be796d8a","id":"deepseek-ai/DeepSeek-R1","private":false,"pipeline_tag":"text-generation","library_name":"transformers","tags":["transformers","safetensors","deepseek_v3","text-generation","conversational","custom_code","arxiv:2501.12948","license:mit","eval-results","text-generation-inference","endpoints_compatible","fp8","deploy:sagemaker","region:us"],"downloads":789555,"likes":13612,"modelId":"deepseek-ai/DeepSeek-R1","author":"deepseek-ai","sha":"56d4cbbb4d29f4355bab4b9a39ccb717a14ad5ad","lastModified":"2025-03-27T04:01:59.000Z","gated":false,"disabled":false,"widgetData":[{"text":"Hi, what can you help me with?"},{"text":"What is 84 * 3 / 2?"},{"text":"Tell me an interesting fact about the universe!"},{"text":"Explain quantum computing in simple terms."}],"model-index":null,"config":{"architectures":["DeepseekV3ForCausalLM"],"auto_map":{"AutoConfig":"configuration_deepseek.DeepseekV3Config","AutoModel":"modeling_deepseek.DeepseekV3Model","AutoModelForCausalLM":"modeling_deepseek.DeepseekV3ForCausalLM"},"model_type":"deepseek_v3","num_experts_per_tok":8,"quantization_config":{"quant_method":"fp8"},"tokenizer_config":{"bos_token":{"__type":"AddedToken","content":"<｜begin▁of▁sentence｜>","lstrip":false,"normalized":true,"rstrip":false,"single_word":false},"eos_token":{"__type":"AddedToken","content":"<｜end▁of▁sentence｜>","lstrip":false,"normalized":true,"rstrip":false,"single_word":false},"pad_token":{"__type":"AddedToken","content":"<｜end▁of▁sentence｜>","lstrip":false,"normalized":true,"rstrip":false,"single_word":false},"unk_token":null,"chat_template":"{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\\n\\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and 'tool_calls' in message %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message['content'] is none %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{'<｜Assistant｜>' + message['content'] + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and 'tool_calls' not in message %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}"}},"cardData":{"license":"mit","library_name":"transformers"},"transformersInfo":{"auto_model":"AutoModelForCausalLM","pipeline_tag":"text-generation","processor":"AutoTokenizer"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"LICENSE"},{"rfilename":"README.md"},{"rfilename":"config.json"},{"rfilename":"configuration_deepseek.py"},{"rfilename":"figures/benchmark.jpg"},{"rfilename":"generation_config.json"},{"rfilename":"model-00001-of-000163.safetensors"},{"rfilename":"model-00002-of-000163.safetensors"},{"rfilename":"model-00003-of-000163.safetensors"},{"rfilename":"model-00004-of-000163.safetensors"},{"rfilename":"model-00005-of-000163.safetensors"},{"rfilename":"model-00006-of-000163.safetensors"},{"rfilename":"model-00007-of-000163.safetensors"},{"rfilename":"model-00008-of-000163.safetensors"},{"rfilename":"model-00009-of-000163.safetensors"},{"rfilename":"model-00010-of-000163.safetensors"},{"rfilename":"model-00011-of-000163.safetensors"},{"rfilename":"model-00012-of-000163.safetensors"},{"rfilename":"model-00013-of-000163.safetensors"},{"rfilename":"model-00014-of-000163.safetensors"},{"rfilename":"model-00015-of-000163.safetensors"},{"rfilename":"model-00016-of-000163.safetensors"},{"rfilename":"model-00017-of-000163.safetensors"},{"rfilename":"model-00018-of-000163.safetensors"},{"rfilename":"model-00019-of-000163.safetensors"},{"rfilename":"model-00020-of-000163.safetensors"},{"rfilename":"model-00021-of-000163.safetensors"},{"rfilename":"model-00022-of-000163.safetensors"},{"rfilename":"model-00023-of-000163.safetensors"},{"rfilename":"model-00024-of-000163.safetensors"},{"rfilename":"model-00025-of-000163.safetensors"},{"rfilename":"model-00026-of-000163.safetensors"},{"rfilename":"model-00027-of-000163.safetensors"},{"rfilename":"model-00028-of-000163.safetensors"},{"rfilename":"model-00029-of-000163.safetensors"},{"rfilename":"model-00030-of-000163.safetensors"},{"rfilename":"model-00031-of-000163.safetensors"},{"rfilename":"model-00032-of-000163.safetensors"},{"rfilename":"model-00033-of-000163.safetensors"},{"rfilename":"model-00034-of-000163.safetensors"},{"rfilename":"model-00035-of-000163.safetensors"},{"rfilename":"model-00036-of-000163.safetensors"},{"rfilename":"model-00037-of-000163.safetensors"},{"rfilename":"model-00038-of-000163.safetensors"},{"rfilename":"model-00039-of-000163.safetensors"},{"rfilename":"model-00040-of-000163.safetensors"},{"rfilename":"model-00041-of-000163.safetensors"},{"rfilename":"model-00042-of-000163.safetensors"},{"rfilename":"model-00043-of-000163.safetensors"},{"rfilename":"model-00044-of-000163.safetensors"},{"rfilename":"model-00045-of-000163.safetensors"},{"rfilename":"model-00046-of-000163.safetensors"},{"rfilename":"model-00047-of-000163.safetensors"},{"rfilename":"model-00048-of-000163.safetensors"},{"rfilename":"model-00049-of-000163.safetensors"},{"rfilename":"model-00050-of-000163.safetensors"},{"rfilename":"model-00051-of-000163.safetensors"},{"rfilename":"model-00052-of-000163.safetensors"},{"rfilename":"model-00053-of-000163.safetensors"},{"rfilename":"model-00054-of-000163.safetensors"},{"rfilename":"model-00055-of-000163.safetensors"},{"rfilename":"model-00056-of-000163.safetensors"},{"rfilename":"model-00057-of-000163.safetensors"},{"rfilename":"model-00058-of-000163.safetensors"},{"rfilename":"model-00059-of-000163.safetensors"},{"rfilename":"model-00060-of-000163.safetensors"},{"rfilename":"model-00061-of-000163.safetensors"},{"rfilename":"model-00062-of-000163.safetensors"},{"rfilename":"model-00063-of-000163.safetensors"},{"rfilename":"model-00064-of-000163.safetensors"},{"rfilename":"model-00065-of-000163.safetensors"},{"rfilename":"model-00066-of-000163.safetensors"},{"rfilename":"model-00067-of-000163.safetensors"},{"rfilename":"model-00068-of-000163.safetensors"},{"rfilename":"model-00069-of-000163.safetensors"},{"rfilename":"model-00070-of-000163.safetensors"},{"rfilename":"model-00071-of-000163.safetensors"},{"rfilename":"model-00072-of-000163.safetensors"},{"rfilename":"model-00073-of-000163.safetensors"},{"rfilename":"model-00074-of-000163.safetensors"},{"rfilename":"model-00075-of-000163.safetensors"},{"rfilename":"model-00076-of-000163.safetensors"},{"rfilename":"model-00077-of-000163.safetensors"},{"rfilename":"model-00078-of-000163.safetensors"},{"rfilename":"model-00079-of-000163.safetensors"},{"rfilename":"model-00080-of-000163.safetensors"},{"rfilename":"model-00081-of-000163.safetensors"},{"rfilename":"model-00082-of-000163.safetensors"},{"rfilename":"model-00083-of-000163.safetensors"},{"rfilename":"model-00084-of-000163.safetensors"},{"rfilename":"model-00085-of-000163.safetensors"},{"rfilename":"model-00086-of-000163.safetensors"},{"rfilename":"model-00087-of-000163.safetensors"},{"rfilename":"model-00088-of-000163.safetensors"},{"rfilename":"model-00089-of-000163.safetensors"},{"rfilename":"model-00090-of-000163.safetensors"},{"rfilename":"model-00091-of-000163.safetensors"},{"rfilename":"model-00092-of-000163.safetensors"},{"rfilename":"model-00093-of-000163.safetensors"},{"rfilename":"model-00094-of-000163.safetensors"},{"rfilename":"model-00095-of-000163.safetensors"},{"rfilename":"model-00096-of-000163.safetensors"},{"rfilename":"model-00097-of-000163.safetensors"},{"rfilename":"model-00098-of-000163.safetensors"},{"rfilename":"model-00099-of-000163.safetensors"},{"rfilename":"model-00100-of-000163.safetensors"},{"rfilename":"model-00101-of-000163.safetensors"},{"rfilename":"model-00102-of-000163.safetensors"},{"rfilename":"model-00103-of-000163.safetensors"},{"rfilename":"model-00104-of-000163.safetensors"},{"rfilename":"model-00105-of-000163.safetensors"},{"rfilename":"model-00106-of-000163.safetensors"},{"rfilename":"model-00107-of-000163.safetensors"},{"rfilename":"model-00108-of-000163.safetensors"},{"rfilename":"model-00109-of-000163.safetensors"},{"rfilename":"model-00110-of-000163.safetensors"},{"rfilename":"model-00111-of-000163.safetensors"},{"rfilename":"model-00112-of-000163.safetensors"},{"rfilename":"model-00113-of-000163.safetensors"},{"rfilename":"model-00114-of-000163.safetensors"},{"rfilename":"model-00115-of-000163.safetensors"},{"rfilename":"model-00116-of-000163.safetensors"},{"rfilename":"model-00117-of-000163.safetensors"},{"rfilename":"model-00118-of-000163.safetensors"},{"rfilename":"model-00119-of-000163.safetensors"},{"rfilename":"model-00120-of-000163.safetensors"},{"rfilename":"model-00121-of-000163.safetensors"},{"rfilename":"model-00122-of-000163.safetensors"},{"rfilename":"model-00123-of-000163.safetensors"},{"rfilename":"model-00124-of-000163.safetensors"},{"rfilename":"model-00125-of-000163.safetensors"},{"rfilename":"model-00126-of-000163.safetensors"},{"rfilename":"model-00127-of-000163.safetensors"},{"rfilename":"model-00128-of-000163.safetensors"},{"rfilename":"model-00129-of-000163.safetensors"},{"rfilename":"model-00130-of-000163.safetensors"},{"rfilename":"model-00131-of-000163.safetensors"},{"rfilename":"model-00132-of-000163.safetensors"},{"rfilename":"model-00133-of-000163.safetensors"},{"rfilename":"model-00134-of-000163.safetensors"},{"rfilename":"model-00135-of-000163.safetensors"},{"rfilename":"model-00136-of-000163.safetensors"},{"rfilename":"model-00137-of-000163.safetensors"},{"rfilename":"model-00138-of-000163.safetensors"},{"rfilename":"model-00139-of-000163.safetensors"},{"rfilename":"model-00140-of-000163.safetensors"},{"rfilename":"model-00141-of-000163.safetensors"},{"rfilename":"model-00142-of-000163.safetensors"},{"rfilename":"model-00143-of-000163.safetensors"},{"rfilename":"model-00144-of-000163.safetensors"},{"rfilename":"model-00145-of-000163.safetensors"},{"rfilename":"model-00146-of-000163.safetensors"},{"rfilename":"model-00147-of-000163.safetensors"},{"rfilename":"model-00148-of-000163.safetensors"},{"rfilename":"model-00149-of-000163.safetensors"},{"rfilename":"model-00150-of-000163.safetensors"},{"rfilename":"model-00151-of-000163.safetensors"},{"rfilename":"model-00152-of-000163.safetensors"},{"rfilename":"model-00153-of-000163.safetensors"},{"rfilename":"model-00154-of-000163.safetensors"},{"rfilename":"model-00155-of-000163.safetensors"},{"rfilename":"model-00156-of-000163.safetensors"},{"rfilename":"model-00157-of-000163.safetensors"},{"rfilename":"model-00158-of-000163.safetensors"},{"rfilename":"model-00159-of-000163.safetensors"},{"rfilename":"model-00160-of-000163.safetensors"},{"rfilename":"model-00161-of-000163.safetensors"},{"rfilename":"model-00162-of-000163.safetensors"},{"rfilename":"model-00163-of-000163.safetensors"},{"rfilename":"model.safetensors.index.json"},{"rfilename":"modeling_deepseek.py"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"}],"spaces":["VIDraft/global-llm-leaderboard","pliny-the-prompter/obliteratus","akhaliq/anycoder","eduagarcia/multilingual-tokenizer-leaderboard","Softedge/AKIRA-SOFTEDGE","abonaie222263/hf-openai-proxy","seawolf2357/LLM_Quantization","llamameta/DeepSeek-R1-Chat-Assistant-Web-Search","FINAL-Bench/all-bench-leaderboard","hadadrjt/ai","Intelligent-Internet/CoT-Lab","KBaba7/Quant","yourbench/advanced","ruslanmv/DeepSeek-R1-Chatbot","FractalAIResearch/Fathom-DeepResearch","openfree/deepseek_r1_API","newmindai/Mezura","2025-ai-timeline/2025-ai-timeline","HPAI-BSC/TuRTLe-Leaderboard","McLoviniTtt/Reasoner4All","bartar/tokenizers","FallnAI/Quantize-HF-Models","openfree/LLM_Quantization","jairwaal/image","bhaskartripathi/LLM_Quantization","MCP-1st-Birthday/Agentic-Codenames-Arena","ruslanmv/convert_to_gguf","seawolf2357/DeepSeek-R1-32b-search","openfree/Korean-Exam-Leaderboard","artificialguybr/CanIRunThisLLM","fdaudens/deepseek-download-stats","shenyunhang/VITA-Audio","umint/openwebui","dream2589632147/Dream-Image-to-Prompt-Pro","Dima123e/deepseek-ai-DeepSeek-R1","awacke1/Deepseek-HPC-GPU-KEDA","SURESHBEEKHANI/financial-assistant-deepseek-r1","Agents-MCP-Hackathon/job-hunting-ai","nazdridoy/inferoxy-hub","totolook/Quant","victor/deepseek-ai-DeepSeek-R12","BarBar288/Chatbot","nikhil-kumar/Financial_Assistant","drdro1/First_agent_template","openfree/DeepSeek-R1-32b-api","victor/deepseek-ai-DeepSeek-R1","K00B404/LLM_Quantization","BeyondHsueh/ReliableMath-Leaderboard","mcjhn/ai","ReallyFloppyPenguin/AstonishingSuperIntelV2","Jakob08/moneychatbot","arudradey/all-bench-leaderboard","abuelzoz33/vram-calculator","ehagey/LLM_Healthcare_Benchmarking","Hkb2001/Medical_Analyzer","UltraRonin/LR2Bench_old","ikun520/deepseek","akhaliq/deepseek-ai-DeepSeek-R1","UltraRonin/LR2Bench","thanhkt/text2manim","zhwang4ai/GenerativeReasoningBenchmark","jinysun/TeLLAgent","kjoof/deepseek-ai-DeepSeek-R1","akra35567/akira","Secondprinsipal/image","tommytracx/anycoder","CatLLM/survey-classifier","MohanamaniDeepika/anycoder","Kodacoda/obliteratus","allabouturmind/Qurio","dumbordumber/obliteratus","joshuasundance/govgis_nov2023-slim-faiss","manojdahal191gom/deepseek-ai-DeepSeek-R1","FutureGadgets/deepseek-ai-DeepSeek-R1","Payknayk/deepseekaiR1","ps2program/deepseek-ai-DeepSeek-R1","rautakshay136/deepseek-ai-DeepSeek-R1","Uener/deepseek-ai-DeepSeek-R1","eikarna/DeepChat","migueldeguzmandev/deepseek-build","kolaslab/DeepSeek-R1-Chatbot-70b","AstarothNomad/deepseek-ai-DeepSeek-R1sansa","PranavNNNNNNNNN/Amma_Project","rayajahan/First_agent_template1","Birkhoff-Archive/DeepClaudeProxy","nathannarrik/TUTOR","Yanz-GPT/yanzgpt-r1-70b-latest","ItayR31/puchifypro","burtenshaw/deepseek-ai-DeepSeek-R1","readomni/literate","Godking0181/deepseek-ai-DeepSeek-R1","Vedantonhf/deepseek-ai-DeepSeek-R1","BarBar288/AI_Tools","umairsiddiquie/deepseek-ai-DeepSeek-R1","huijio/chatinterface","Thsuporte24h/Olkchat","amaansksz/Intromate","chipling/api","AmirFARES/Datamir-Hub-Assistant","niuzi66/deepseek-ai-DeepSeek-R1"],"createdAt":"2025-01-20T03:46:07.000Z","safetensors":{"parameters":{"BF16":3918786560,"F8_E4M3":680571043840,"F32":41555600},"total":684531386000},"inference":"warm","usedStorage":688624501744}