{"_id":"63fe4c6c0b9bcde2f005463a","id":"EleutherAI/pythia-12b","private":false,"pipeline_tag":"text-generation","library_name":"transformers","tags":["transformers","pytorch","safetensors","gpt_neox","text-generation","causal-lm","pythia","en","dataset:EleutherAI/pile","arxiv:2304.01373","arxiv:2101.00027","arxiv:2201.07311","license:apache-2.0","text-generation-inference","endpoints_compatible","deploy:azure","region:us"],"downloads":25869,"likes":145,"modelId":"EleutherAI/pythia-12b","author":"EleutherAI","sha":"bb1e3e710cdf6b524461d543cfb5ba773f0a81b6","lastModified":"2024-07-09T15:50:54.000Z","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":["GPTNeoXForCausalLM"],"model_type":"gpt_neox","tokenizer_config":{"bos_token":"<|endoftext|>","eos_token":"<|endoftext|>","unk_token":"<|endoftext|>"}},"cardData":{"language":["en"],"tags":["pytorch","causal-lm","pythia"],"license":"apache-2.0","datasets":["EleutherAI/pile"]},"transformersInfo":{"auto_model":"AutoModelForCausalLM","pipeline_tag":"text-generation","processor":"AutoTokenizer"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"config.json"},{"rfilename":"eval_plots/arc_challenge.png"},{"rfilename":"eval_plots/arc_easy_v1.png"},{"rfilename":"eval_plots/lambada_openai.png"},{"rfilename":"eval_plots/lambada_openai_v1.png"},{"rfilename":"eval_plots/piqa.png"},{"rfilename":"eval_plots/piqa_v1.png"},{"rfilename":"eval_plots/sciq.png"},{"rfilename":"eval_plots/sciq_v1.png"},{"rfilename":"eval_plots/winogrande.png"},{"rfilename":"eval_plots/winogrande_v1.png"},{"rfilename":"model-00001-of-00003.safetensors"},{"rfilename":"model-00002-of-00003.safetensors"},{"rfilename":"model-00003-of-00003.safetensors"},{"rfilename":"model.safetensors.index.json"},{"rfilename":"pytorch_model-00001-of-00003.bin"},{"rfilename":"pytorch_model-00002-of-00003.bin"},{"rfilename":"pytorch_model-00003-of-00003.bin"},{"rfilename":"pytorch_model.bin.index.json"},{"rfilename":"special_tokens_map.json"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"}],"spaces":["pliny-the-prompter/obliteratus","Intel/low_bit_open_llm_leaderboard","seawolf2357/LLM_Quantization","h2oai/h2ogpt-chatbot","eduagarcia/open_pt_llm_leaderboard","h2oai/h2ogpt-chatbot2","BAAI/open_cn_llm_leaderboard","Sharathhebbar24/One-stop-for-Open-source-models","qiantong-xu/toolbench-leaderboard","gsaivinay/open_llm_leaderboard","KBaba7/Quant","EvanTHU/MotionLLM","FallnAI/Quantize-HF-Models","openfree/LLM_Quantization","GTBench/GTBench","Vikhrmodels/small-shlepa-lb","bhaskartripathi/LLM_Quantization","ruslanmv/convert_to_gguf","BAAI/open_flageval_vlm_leaderboard","BAAI/FlagEval-Robo","lapsapking/h2ogpt-chatbot","OPTML-Group/UnlearnCanvas-Benchmark","felixz/open_llm_leaderboard","Vikhrmodels/Russian_Arena_General","HemaAM/GPT_train_on_LLaMa","anantgupta129/LitGPT-Pythia-160M","Vikhrmodels/small-shlepa","totolook/Quant","K00B404/LLM_Quantization","b1sheng/kg_llm_leaderboard_test","Zulelee/langchain-chatchat","Kodacoda/obliteratus","dumbordumber/obliteratus","PrarthanaTS/tsai-gpt-from-scratch","MadhurGarg/TSAIGPTRedPajama","RaviNaik/ERA-SESSION22","neubla/neubla-llm-evaluation-board","rodrigomasini/data_only_open_llm_leaderboard","Docfile/open_llm_leaderboard","his0/h2ogpt-chatbot","atimughal662/InfoFusion","Sijuade/GPTNEXTWORD","Oss11/Quantize-HF-Models","Xlnk/Quantize-HF-Models","exploitz3r0bbd/Quantize-HF-Models","dromero14521/obliteratus","kicfk/obliteratus","aaahmet/obliteratus","rbinrs/obliteratus","Ngixdev/obliteratus","Deadmon/obliteratus","RavichandranJ/obliteratus","S-Dreamer/obliteratus","AlanaSky/asgaard","marchkamal51/obliteratus","trhacknon/h2ogpt-chatbot","vs4vijay/h2ogpt-chatbot","akashkj/H2OGPT","ariel0330/h2osiri","elitecode/h2ogpt-chatbot2","ccoreilly/aigua-xat","piyushgrover/MiniGPT_S22","supra-e-acc/Pythia-160M-text-generate","venkyyuvy/GPT_redpajama","VarunSivamani/GPT-From-Scratch","mkthoma/GPT_From_Scratch","sanjanatule/GPTNext","Sambhavnoobcoder/h2ogpt-chatbot","RashiAgarwal/TSAIGPTRedPajama","neuralorbs/DialogGen","Navyabhat/ERAV1-Session-22","GunaKoppula/ERA-Session-22","Rockylxl/EleutherAI-pythia-12b","Vaish2705/ERA_S22","smothiki/open_llm_leaderboard","pngwn/open_llm_leaderboard","pngwn/open_llm_leaderboard_two","iblfe/test","AnonymousSub/Ayurveda_Chatbot","K00B404/Research-chatbot","wissamantoun/LLM_Detection_Attribution","0x1668/open_llm_leaderboard","pngwn/open_llm_leaderboard-check","asir0z/open_llm_leaderboard","kelvin-t-lu/chatbot","kbmlcoding/open_llm_leaderboard_free","debisoft/dolly-v0-70m","ToletiSri/TSAI_S22","K00B404/One-stop-till-you-drop","aichampions/open_llm_leaderboard","Adeco/open_llm_leaderboard","anirudh937/open_llm_leaderboard","smothiki/open_llm_leaderboard2","cw332/h2ogpt-chatbot","mjalg/IFEvalTR","lastsamuraii/LitGPT-Pythia-160M","abugaber/aiben","abugaber/test","K00B404/convert_to_gguf","GTOMA83/Quantize-HF-Models"],"createdAt":"2023-02-28T18:48:12.000Z","safetensors":{"parameters":{"F16":11846072896,"U8":150994944},"total":11997067840},"usedStorage":3685421391454}