{"_id":"6797d65120c7240ceda5c1b8","id":"allenai/OLMoE-1B-7B-0125-Instruct","private":false,"pipeline_tag":"text-generation","library_name":"transformers","tags":["transformers","safetensors","olmoe","text-generation","conversational","en","dataset:allenai/RLVR-GSM","arxiv:2409.02060","arxiv:2411.15124","base_model:allenai/OLMoE-1B-7B-0125-DPO","base_model:finetune:allenai/OLMoE-1B-7B-0125-DPO","license:apache-2.0","endpoints_compatible","region:us"],"downloads":142081,"likes":68,"modelId":"allenai/OLMoE-1B-7B-0125-Instruct","author":"allenai","sha":"b89a7c4bc24fb9e55ce2543c9458ce0ca5c4650e","lastModified":"2025-02-04T16:47:15.000Z","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":["OlmoeForCausalLM"],"model_type":"olmoe","num_experts":64,"num_experts_per_tok":8,"tokenizer_config":{"bos_token":"|||IP_ADDRESS|||","chat_template":"{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n'  + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n'  + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}","eos_token":"|||IP_ADDRESS|||","pad_token":"<pad>","unk_token":null}},"cardData":{"license":"apache-2.0","language":["en"],"pipeline_tag":"text-generation","base_model":["allenai/OLMoE-1B-7B-0125-DPO"],"library_name":"transformers","datasets":["allenai/RLVR-GSM"]},"transformersInfo":{"auto_model":"AutoModelForCausalLM","pipeline_tag":"text-generation","processor":"AutoTokenizer"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"config.json"},{"rfilename":"generation_config.json"},{"rfilename":"model-00001-of-00003.safetensors"},{"rfilename":"model-00002-of-00003.safetensors"},{"rfilename":"model-00003-of-00003.safetensors"},{"rfilename":"model.safetensors.index.json"},{"rfilename":"special_tokens_map.json"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"}],"spaces":["tardellirs/model-pulse","aquanode/gpu-vram-calculator","oimiragieo/mine-your-moe-atlas"],"createdAt":"2025-01-27T18:54:09.000Z","safetensors":{"parameters":{"BF16":6919161856},"total":6919161856},"usedStorage":581226322320}