huggingface/alignment-handbook
View on GitHubRobust recipes to align language models with human and AI preferences
- Stars
- 5.7k
- Forks
- 490
- Open beginner issues
- 0
- Indexed issues
- 92
- Avg merge
- 2m
- Merged PRs (30d)
- 1
- Dominant language
- Python
- License
- Apache-2.0
- Last GitHub push
- Apr 8, 2026
- Latest indexed
- Sep 17, 2026
- Contributing guide
- No contributing guide
- Code of conduct
- No code of conduct
- Beginner labels
- No beginner labels indexed
-
huggingface/alignment-handbook#7 · 1 comment · 7 reactions · 0 assignees ·
-
huggingface/alignment-handbook#8 · 3 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#9 · 2 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#15 · 1 comment · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#16 · 4 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#22 · 13 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#24 · 1 comment · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#25 · 0 comments · 6 reactions · 0 assignees ·
-
huggingface/alignment-handbook#26 · 1 comment · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#27 · 3 comments · 1 reaction · 0 assignees ·
-
Train on emails Open
huggingface/alignment-handbook#28 · 2 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#29 · 0 comments · 0 reactions · 0 assignees ·
-
Max Sequence Length Open
huggingface/alignment-handbook#32 · 0 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#34 · 0 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#36 · 2 comments · 1 reaction · 0 assignees ·
-
DPO loss Open
huggingface/alignment-handbook#38 · 8 comments · 0 reactions · 0 assignees ·
-
Why zephyr-7b-dpo-lora is finetuned from mistralai/Mistral-7B-v0.1 instead of zepher-7b-sft model? Open
huggingface/alignment-handbook#39 · 2 comments · 2 reactions · 0 assignees ·
-
Windows installation Open
huggingface/alignment-handbook#41 · 0 comments · 1 reaction · 0 assignees ·
-
huggingface/alignment-handbook#42 · 4 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#44 · 7 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#45 · 27 comments · 0 reactions · 0 assignees ·
-
Weird DPO loss Open
huggingface/alignment-handbook#46 · 1 comment · 4 reactions · 0 assignees ·
-
huggingface/alignment-handbook#47 · 6 comments · 1 reaction · 0 assignees ·
-
huggingface/alignment-handbook#52 · 0 comments · 6 reactions · 0 assignees ·
-
huggingface/alignment-handbook#55 · 1 comment · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#56 · 3 comments · 1 reaction · 0 assignees ·
-
bug
huggingface/alignment-handbook#57 · 7 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#59 · 7 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#61 · 3 comments · 2 reactions · 0 assignees ·
-
huggingface/alignment-handbook#62 · 0 comments · 1 reaction · 0 assignees ·
-
huggingface/alignment-handbook#63 · 1 comment · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#65 · 0 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#67 · 0 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#68 · 1 comment · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#69 · 1 comment · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#72 · 1 comment · 2 reactions · 0 assignees ·
-
huggingface/alignment-handbook#73 · 5 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#74 · 3 comments · 8 reactions · 0 assignees ·
-
huggingface/alignment-handbook#75 · 0 comments · 3 reactions · 0 assignees ·
-
huggingface/alignment-handbook#77 · 0 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#78 · 3 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#79 · 1 comment · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#82 · 1 comment · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#85 · 1 comment · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#90 · 0 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#91 · 1 comment · 0 reactions · 0 assignees ·
-
jinja2.exceptions.TemplateError: Conversation roles must alternate user/assistant/user/assistant/... Open
huggingface/alignment-handbook#93 · 2 comments · 0 reactions · 0 assignees ·
-
huggingface/alignment-handbook#98 · 0 comments · 3 reactions · 0 assignees ·
-
huggingface/alignment-handbook#99 · 0 comments · 2 reactions · 0 assignees ·
-
huggingface/alignment-handbook#103 · 0 comments · 0 reactions · 0 assignees ·