{"full_name":"huggingface/alignment-handbook","owner":"huggingface","name":"alignment-handbook","shard":"1","url":"https://github.com/huggingface/alignment-handbook","description":"Robust recipes to align language models with human and AI preferences","homepage":"https://huggingface.co/HuggingFaceH4","topics":["llm","rlhf","transformers"],"tag_pages":["llm","rlhf","transformers"],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/25720743?v=4","created_at":"2023-08-25T11:35:34Z","pushed_at":"2026-09-23T14:09:25Z","metrics":{"stars":5715,"forks":496,"watchers":103,"issues":147,"prs":92,"releases":0,"issues_open":92,"issues_closed":55,"prs_open":8,"prs_closed":18,"prs_merged":66,"discussions":0},"growth":{"day":{"stars":2,"forks":0,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[5711,5712,5712,5712,5712,5713,5715],"forks":[496,496,496,496,496,496,496],"watchers":[null,103,103,103,103,103,103],"issues_open":[null,92,92,92,92,92,92],"prs_open":[null,8,8,8,8,8,8]},"boards":{},"same_owner":[{"full_name":"huggingface/transformers","name":"transformers","shard":"1","boards":{"total":54}},{"full_name":"huggingface/OpenEnv","name":"OpenEnv","shard":"1","boards":{}},{"full_name":"huggingface/accelerate","name":"accelerate","shard":"1","boards":{}},{"full_name":"huggingface/agents-course","name":"agents-course","shard":"1","boards":{}},{"full_name":"huggingface/diffusers","name":"diffusers","shard":"1","boards":{}},{"full_name":"huggingface/ml-intern","name":"ml-intern","shard":"1","boards":{}},{"full_name":"huggingface/parler-tts","name":"parler-tts","shard":"1","boards":{}},{"full_name":"huggingface/pytorch-image-models","name":"pytorch-image-models","shard":"1","boards":{}},{"full_name":"huggingface/sentence-transformers","name":"sentence-transformers","shard":"1","boards":{}},{"full_name":"huggingface/skills","name":"skills","shard":"1","boards":{}},{"full_name":"huggingface/smolagents","name":"smolagents","shard":"1","boards":{}},{"full_name":"huggingface/speech-to-speech","name":"speech-to-speech","shard":"1","boards":{}},{"full_name":"huggingface/transformers.js","name":"transformers.js","shard":"1","boards":{}},{"full_name":"huggingface/trl","name":"trl","shard":"1","boards":{}}],"issues":[{"number":45,"title":"Reproducing of Lora Model  Result on MT-Bench","comments":27,"created_at":"2023-11-22T03:42:32Z"},{"number":22,"title":"How to perform full parameter finetuning without A100 GPUs","comments":13,"created_at":"2023-11-14T01:33:41Z"},{"number":38,"title":"DPO loss","comments":8,"created_at":"2023-11-17T17:30:13Z"},{"number":125,"title":"Major bug: Chat template is not actually applied in run_sft.py and run_dpo.py","comments":7,"created_at":"2024-02-23T17:06:53Z"},{"number":59,"title":"Get this error on run_sft.py when calling \"trainer.push_to_hub\": [Rank 0] Watchdog caught collective operation timeout","comments":7,"created_at":"2023-12-01T08:48:04Z"},{"number":57,"title":"\"RuntimeError: The size of tensor a (0) must match the size of tensor b (4096) at non-singleton dimension 1\" (DPO + LoRA)","comments":7,"created_at":"2023-11-28T23:55:20Z"},{"number":44,"title":"Global batch size question","comments":7,"created_at":"2023-11-21T15:13:00Z"},{"number":159,"title":"FSDP + QDoRA Support","comments":6,"created_at":"2024-04-24T06:53:52Z"}],"discussions":[],"latest_release":null,"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}