{
 "repo": "EleutherAI/lm-evaluation-harness",
 "url": "https://github.com/EleutherAI/lm-evaluation-harness",
 "what": "The LM Evaluation Harness is EleutherAI's framework for few-shot evaluation of language models. One lm_eval command scores a model on named tasks, with backends for Hugging Face transformers, vLLM, SGLang, llama.cpp servers, ONNX Runtime, NeMo, Megatron and any OpenAI compatible API. It supports multi GPU evaluation, result saving, response logging and pushing results to the Hugging Face Hub.",
 "language": "",
 "stars": null,
 "gain": null,
 "created": "",
 "uc_n": 3,
 "title": "LM Evaluation Harness",
 "show": true,
 "what_source": "deduped",
 "use_cases": "https://dedupedai.com/use-cases/eleutherai-lm-evaluation-harness/",
 "use_cases_json": "https://dedupedai.com/use-cases/r/eleutherai-lm-evaluation-harness.json",
 "json": "https://dedupedai.com/repos/r/eleutherai-lm-evaluation-harness.json",
 "slug": "eleutherai-lm-evaluation-harness",
 "api": "https://dedupedai.com/api/v1/repos/eleutherai-lm-evaluation-harness.json",
 "api_version": "v1"
}