huggingface alignment-handbook issues

huggingface / alignment-handbook

Robust recipes to align language models with human and AI preferences

https://huggingface.co/HuggingFaceH4

Apache License 2.0

4.28k stars 367 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Max Sequence Length

#32 ujjawalmadan opened 8 months ago
0
Missing config params on SFT

#31 tcapelle closed 8 months ago
0
Fix `apply_chat_template` function for `dpo` and unknown `task`

#30 alvarobartt closed 8 months ago
0
Release dSFT data preparation (self-instruct) code?

#29 nlpcat opened 8 months ago
0
Train on emails

#28 patchie opened 8 months ago
2
Reproducing SFT results.

#27 tcapelle opened 8 months ago
3
Question about the evaluation dataset

#26 chenweixin107 opened 8 months ago
1
Question about DPO learning rate - comparison to neural-chat-7b-v3 training

#25 sebastianschramm opened 8 months ago
0
Training Interruptions and Epoch Skipping with 6 Billion Parameter Model on 8 A100 GPUs

#24 apt-team-018 opened 8 months ago
1
Running on single RTX4090

#23 jasonwtli closed 8 months ago
1
How to perform full parameter finetuning without A100 GPUs

#22 ChenDRAG opened 8 months ago
13
The deepspeed full finetunning get stuck.

#21 ChenDRAG closed 8 months ago
1
Fix note syntax highlighting in `README.md`

#20 alvarobartt closed 8 months ago
2
Fix image alignment

#19 lewtun closed 8 months ago
0
Add moar explanations

#18 lewtun closed 8 months ago
0
fix typos in readmes

#17 kashif closed 8 months ago
0
Memory Issue with 7b Model Fine-Tuning on 6 H100 GPUs

#16 apt-team-018 opened 8 months ago
4
LoRA + FlashAttention2 speed up？

#15 zhoumengbo opened 8 months ago
1
Resolves #13 fix typo in zephyr recipe readme

#14 sebastianschramm closed 8 months ago
0
Typo in example commands in zephyr recipe readme

#13 sebastianschramm closed 8 months ago
0
Differences between alpha and beta models

#12 liutianlin0121 closed 8 months ago
2
Code release

#11 lewtun closed 8 months ago
0
Is it possible to visualize the loss graph during fine-tuning from Mistral to Zephyr?

#10 sooftware closed 8 months ago
2
How to finetune or lora on custom dataset

#9 universewill opened 8 months ago
1
Is there available SFT fine tuning for zephyr-7B families?

#8 daehuikim opened 9 months ago
3
Questions about data filtering for zephyr-7b-beta's UltraChat version

#7 jc-ryan opened 9 months ago
1
code release?

#6 renjie130 closed 8 months ago
6
SFT checkpoint of zephyr-7b

#5 liutianlin0121 closed 9 months ago
4
fix: remove useless token

#4 rtrompier closed 9 months ago
0
Great initiative - can you please share timeline?

#3 samuelazran closed 6 months ago
2
Fix README typos

#2 anakin87 closed 9 months ago
0
Doc builder testing PR

#1 natolambert closed 11 months ago
2