Skip to content

Issues: huggingface/trl

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

55 Open 870 Closed
55 Open 870 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

There is no chat_template of the model used when constructing data in DPOTrainer
#1687 opened Jun 1, 2024 by mst272
vsft_llava: ValueError: Expected input batch_size (78528) to match target batch_size (41728).
#1685 opened May 31, 2024 by kishan-character
1
Feature Request: Simple Preference Optimization Integration
#1684 opened May 30, 2024 by 1485840691-eng
SFTrainer with FSDP on a model that doens't fit in GPU memory
#1681 opened May 29, 2024 by tambulkar
Possible risks in xxxPOTrainer
#1679 opened May 29, 2024 by AIR-hl
3
Why compute IPO loss using average_log_prob=Ture？
#1677 opened May 28, 2024 by AIR-hl
2
ppov2 & rloo trainer doesn't correctly compute reward if reward tokenizer is different from policy tokenizer
#1674 opened May 28, 2024 by TheBlackCat22
SFT Trainer Packing Validation
#1672 opened May 28, 2024 by alex-jw-brooks
1
Path for support generative eval in DPOTrainer
#1671 opened May 27, 2024 by prompteus
1
ImportError: cannot import name 'SFTScriptArguments' from 'trl.commands.cli_utils' & --report_to flag
#1669 opened May 26, 2024 by alielfilali01
1
Llama 3 Unsloth Fixes
#1668 opened May 26, 2024 by lhl
OOM with DPO Trainer on A100 GPU
#1667 opened May 25, 2024 by JhonDan1999
1
Bug in DPO trainning example
#1666 opened May 24, 2024 by AIR-hl
FineTuning issue with Gemma-2B-IT model using the SFTTrainer
#1665 opened May 23, 2024 by AvisP
2
Can we use SFTTrainer for pre-training?
#1657 opened May 23, 2024 by wennycooper
5
DPOTrainer deepspeed.initialize cause ref_model not fixed
#1652 opened May 22, 2024 by shuoYan97
1
KTO finetuning - float division by zero
#1651 opened May 22, 2024 by jetlime
1
how to save v_head
#1650 opened May 20, 2024 by zyzhang1130
2
Adapter name for SFT trainer
#1649 opened May 18, 2024 by para-zhou
1
Set seed
#1648 opened May 17, 2024 by user799595
1
ValueError when training on a multi GPU setup and DPO
#1645 opened May 16, 2024 by miosturu
How to save and resume a checkpoint from PPOTrainer
#1643 opened May 14, 2024 by paraGONG
ImportError: cannot import name 'DPOConfig' from 'trl'
#1642 opened May 14, 2024 by AswiniNLP
17
Do we need to consider the chat template when doing DPO/KTO training? DPO Question related to DPO and DPOTrainer KTO
#1640 opened May 11, 2024 by ZeroYuHuang
2
ImportError: cannot import name 'SFTConfig' from 'trl'
#1639 opened May 11, 2024 by brand17
3
ProTip! Find all open issues with in progress development work with linked:pr.