{"_id":"666bbd0e0f82f95f338669c7","id":"deepseek-ai/DeepSeek-Coder-V2-Instruct","private":false,"pipeline_tag":"text-generation","library_name":"transformers","tags":["transformers","safetensors","deepseek_v2","text-generation","conversational","custom_code","arxiv:2401.06066","base_model:deepseek-ai/DeepSeek-Coder-V2-Base","base_model:finetune:deepseek-ai/DeepSeek-Coder-V2-Base","license:other","eval-results","text-generation-inference","endpoints_compatible","region:us"],"downloads":10423,"likes":701,"modelId":"deepseek-ai/DeepSeek-Coder-V2-Instruct","author":"deepseek-ai","sha":"2453c79a2a0947968a054947b53daa598cb3be52","lastModified":"2024-08-21T06:42:50.000Z","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":["DeepseekV2ForCausalLM"],"auto_map":{"AutoConfig":"configuration_deepseek.DeepseekV2Config","AutoModel":"modeling_deepseek.DeepseekV2Model","AutoModelForCausalLM":"modeling_deepseek.DeepseekV2ForCausalLM"},"model_type":"deepseek_v2","num_experts_per_tok":6,"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 %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"}},"cardData":{"license":"other","license_name":"deepseek-license","license_link":"LICENSE","base_model":"deepseek-ai/DeepSeek-Coder-V2-Base"},"transformersInfo":{"auto_model":"AutoModelForCausalLM","pipeline_tag":"text-generation","processor":"AutoTokenizer"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"config.json"},{"rfilename":"configuration_deepseek.py"},{"rfilename":"generation_config.json"},{"rfilename":"model-00001-of-000055.safetensors"},{"rfilename":"model-00002-of-000055.safetensors"},{"rfilename":"model-00003-of-000055.safetensors"},{"rfilename":"model-00004-of-000055.safetensors"},{"rfilename":"model-00005-of-000055.safetensors"},{"rfilename":"model-00006-of-000055.safetensors"},{"rfilename":"model-00007-of-000055.safetensors"},{"rfilename":"model-00008-of-000055.safetensors"},{"rfilename":"model-00009-of-000055.safetensors"},{"rfilename":"model-00010-of-000055.safetensors"},{"rfilename":"model-00011-of-000055.safetensors"},{"rfilename":"model-00012-of-000055.safetensors"},{"rfilename":"model-00013-of-000055.safetensors"},{"rfilename":"model-00014-of-000055.safetensors"},{"rfilename":"model-00015-of-000055.safetensors"},{"rfilename":"model-00016-of-000055.safetensors"},{"rfilename":"model-00017-of-000055.safetensors"},{"rfilename":"model-00018-of-000055.safetensors"},{"rfilename":"model-00019-of-000055.safetensors"},{"rfilename":"model-00020-of-000055.safetensors"},{"rfilename":"model-00021-of-000055.safetensors"},{"rfilename":"model-00022-of-000055.safetensors"},{"rfilename":"model-00023-of-000055.safetensors"},{"rfilename":"model-00024-of-000055.safetensors"},{"rfilename":"model-00025-of-000055.safetensors"},{"rfilename":"model-00026-of-000055.safetensors"},{"rfilename":"model-00027-of-000055.safetensors"},{"rfilename":"model-00028-of-000055.safetensors"},{"rfilename":"model-00029-of-000055.safetensors"},{"rfilename":"model-00030-of-000055.safetensors"},{"rfilename":"model-00031-of-000055.safetensors"},{"rfilename":"model-00032-of-000055.safetensors"},{"rfilename":"model-00033-of-000055.safetensors"},{"rfilename":"model-00034-of-000055.safetensors"},{"rfilename":"model-00035-of-000055.safetensors"},{"rfilename":"model-00036-of-000055.safetensors"},{"rfilename":"model-00037-of-000055.safetensors"},{"rfilename":"model-00038-of-000055.safetensors"},{"rfilename":"model-00039-of-000055.safetensors"},{"rfilename":"model-00040-of-000055.safetensors"},{"rfilename":"model-00041-of-000055.safetensors"},{"rfilename":"model-00042-of-000055.safetensors"},{"rfilename":"model-00043-of-000055.safetensors"},{"rfilename":"model-00044-of-000055.safetensors"},{"rfilename":"model-00045-of-000055.safetensors"},{"rfilename":"model-00046-of-000055.safetensors"},{"rfilename":"model-00047-of-000055.safetensors"},{"rfilename":"model-00048-of-000055.safetensors"},{"rfilename":"model-00049-of-000055.safetensors"},{"rfilename":"model-00050-of-000055.safetensors"},{"rfilename":"model-00051-of-000055.safetensors"},{"rfilename":"model-00052-of-000055.safetensors"},{"rfilename":"model-00053-of-000055.safetensors"},{"rfilename":"model-00054-of-000055.safetensors"},{"rfilename":"model-00055-of-000055.safetensors"},{"rfilename":"model.safetensors.index.json"},{"rfilename":"modeling_deepseek.py"},{"rfilename":"tokenization_deepseek_fast.py"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"}],"spaces":["FallnAI/Quantize-HF-Models","eduagarcia/multilingual-tokenizer-leaderboard","KBaba7/Quant","openfree/LLM_Quantization","bhaskartripathi/LLM_Quantization","ruslanmv/convert_to_gguf","seawolf2357/LLM_Quantization","totolook/Quant","cstr/PDF-Summarizer","K00B404/LLM_Quantization","TheLoopStudio/CoderAI","aliceblue11/logo_o1-preview","nbroad/HF-API-monitor","hamxa500/deepseek-ai-DeepSeek-Coder-V2-Instruct","martinakaduc/melt","SUHHHH/LLMpromt","joshuaXX/deepseek-ai-DeepSeek-Coder-V2-Instruct","Oss11/Quantize-HF-Models","Xlnk/Quantize-HF-Models","exploitz3r0bbd/Quantize-HF-Models","dhlak/llm-vram-calc","evelyn-lo/evelyn","abhillubillu/gameapp","itsjakeo/deepseek-ai-DeepSeek-Coder-V2-Instruct","zjasper666/bf16_vs_fp8","HuggingFaceSupport/deepseek-ai-DeepSeek-Coder-V2-Instruct","testcs/deepseek-ai-DeepSeek-Coder-V2-Instruct","SUHHHH/openLLMchatbot","SG34/openLLMchatbot","aliceblue11/openLLMchatbot111","aliceblue11/openLLMchatbot222","aliceblue11/LLMpromt111","SG34/LLMpromt","SUHHHH/USEB-COPY","aliceblue11/LLMpromt222","SUHHHH/LLMpromt-test","superrich001/LLMpromt","aliceblue11/LLMpromt333","basantakhakurel/deepseek-ai-DeepSeek-Coder-V2-Instruct","SternLee04/trialSpace","SternLee04/deepseek-ai-DeepSeek-Coder-V2-Instruct","clay990/deepseek-ai-DeepSeek-Coder-V2-Instruct","Brano892H9/deepseek-ai-DeepSeek-Coder-V2-Instruct","whoamiii/deepseek-ai-DeepSeek-Coder-V2-Instruct","cartr117/deepseek-ai-DeepSeek-Coder-V2-Instruct","cnyt947/deepseek-ai-DeepSeek-Coder-V2-Instruct","mendoanjoe/deepseek-ai-DeepSeek-Coder-V2-Instruct","tpdph/deepseek-ai-DeepSeek-Coder-V2-Instruct","IdenGhost/deepseek-ai-DeepSeek-Coder-V2-Instruct","baranbayden/coderv2","alanerkenov317/deepseek-ai-DeepSeek-Coder-V2-Instruct","msun415/Llamole","Examon1/Examon4u","diamond-in/deepseek-ai-DeepSeek-Coder-V2-Instruct","KuberMehta/PolyThink-Alpha","rayaaas/deepseek-ai-DeepSeek-Coder-V2-Instruct","davidizzle/LIA_CodiceDaVinci","sam522/Coding_bot","garyuzair/SEO-Content-Generator","diagmaster/diagmaster-coder","ama2aifusion/agents-course-final-project","krzsam/Agents-Course-Assignment","K00B404/convert_to_gguf","natabrizy/testapp","deebee7/moltbot-hybrid-engine","GTOMA83/Quantize-HF-Models","apaxray/Beta_AOC","VedantShirgaonkar/datathon-agents","Jimlkh/OuluDemo","SERGEI8756/dddddddddddd","Guilherme34/convert_to_gguf","Ashketchum007/Code-demo","usku880/Code-reviwer-v2","dryymatt/wizard-vibe-studio","alch396/deepseek-ai-DeepSeek-Coder-V2-Instruct","Waheed786dar/my-ai-api","Waheed786dar/Aiii","GTO83/LLM_Quantization"],"createdAt":"2024-06-14T03:46:22.000Z","safetensors":{"parameters":{"BF16":235741434880},"total":235741434880},"usedStorage":471486512925}