Skip to content

Issues: huggingface/alignment-handbook

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
92 Open 50 Closed
92 Open 50 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Training Finishes Prematurely after Max Length increases
#36 opened Nov 17, 2023 by ujjawalmadan
2
How to finetune or lora on custom dataset
#9 opened Nov 5, 2023 by universewill
2
LoRA + FlashAttention2 speed up？
#15 opened Nov 11, 2023 by zhoumengbo
1
Memory Issue with 7b Model Fine-Tuning on 6 H100 GPUs
#16 opened Nov 11, 2023 by apt-team-018
4
How to perform full parameter finetuning without A100 GPUs
#22 opened Nov 14, 2023 by ChenDRAG
13
Training Interruptions and Epoch Skipping with 6 Billion Parameter Model on 8 A100 GPUs
#24 opened Nov 14, 2023 by apt-team-018
1
Question about DPO learning rate - comparison to neural-chat-7b-v3 training
#25 opened Nov 14, 2023 by sebastianschramm
Question about the evaluation dataset
#26 opened Nov 14, 2023 by chenweixin107
1
Reproducing SFT results.
#27 opened Nov 14, 2023 by tcapelle
3
Train on emails
#28 opened Nov 14, 2023 by patchie
2
Release dSFT data preparation (self-instruct) code?
#29 opened Nov 15, 2023 by nlpcat
Max Sequence Length
#32 opened Nov 15, 2023 by ujjawalmadan
Questions about data filtering for zephyr-7b-beta's UltraChat version
#7 opened Oct 29, 2023 by jc-ryan
1
Misalignment between config_lora.yaml and the model card
#34 opened Nov 16, 2023 by ChenDRAG
Question about "ModuleNotFoundError: No module named 'alignment'"
#37 opened Nov 17, 2023 by liugangdao
2
DPO loss
#38 opened Nov 17, 2023 by JiuhaiChen
8
Why zephyr-7b-dpo-lora is finetuned from mistralai/Mistral-7B-v0.1 instead of zepher-7b-sft model?
#39 opened Nov 17, 2023 by ChenDRAG
2
Windows installation
#41 opened Nov 20, 2023 by NicolasMejiaPetit
How to QLoRA training with ZeRO-3 on two or more GPUs?
#42 opened Nov 20, 2023 by Di-Zayn
4
Global batch size question
#44 opened Nov 21, 2023 by liutianlin0121
7
Reproducing of Lora Model Result on MT-Bench
#45 opened Nov 22, 2023 by wlhgtc
27
Weird DPO loss
#46 opened Nov 24, 2023 by ChenDRAG
1
Tokenizer model_max_length
#47 opened Nov 24, 2023 by binarycrayon
6
What about the system prompt?
#52 opened Nov 27, 2023 by timothylimyl
Warning: Could not find flash_attn
#213 opened Feb 28, 2025 by AetherPrior
ProTip! Adding no:label will show everything without a label.