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

119 Open 1,186 Closed
119 Open 1,186 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

Different finetune speed in DPO task of peft and ms-swift (600/S iter vs 30/s iter)
#2536 opened Jan 2, 2025 by maoulee
7 of 9 tasks
(Willing to PR) Will it be welcomed if speeding up algorithms like PPO and code refactor/cleanup? 🏋 PPO Related to PPO 🏋 RLOO Related to RLOO
#2535 opened Dec 31, 2024 by fzyzcjy
Using "beam search" strategy while generating the responses 🙋 help from community wanted Open invitation for community members to contribute 🏋 PPO Related to PPO
#2534 opened Dec 31, 2024 by SachinVashisth
onlinedpo error when use deepspeed zero3 🐛 bug Something isn't working 🚀 deepspeed Related to deepspeed 🏋 Online DPO Related to Online DPO
#2532 opened Dec 30, 2024 by yiyepiaoling0715
5 of 9 tasks
2
PPOTrainer: num_mini_batches setting affects training progress bar in an unexpected way 🐛 bug Something isn't working 🏋 PPO Related to PPO
#2530 opened Dec 29, 2024 by dawidm
6 of 9 tasks
1
Option to disable unwrapping model for generation in PPO/RLOO/OnlineDPO ✨ enhancement New feature or request 🏋 Online DPO Related to Online DPO 🏋 PPO Related to PPO 🏋 RLOO Related to RLOO
#2529 opened Dec 28, 2024 by dawidm
1
Direct Q-Function Optimization ✨ enhancement New feature or request
#2526 opened Dec 28, 2024 by catherinelee274
Integrate OREO into TRL and HF ✨ enhancement New feature or request
#2525 opened Dec 28, 2024 by August-murr
3 tasks done
@August-murr
How to solve the situation where the tokenizer of the reward model is inconsistent with the tokenizer of the actor model？ ❓ question Seeking clarification or more information
#2523 opened Dec 27, 2024 by stephen-nju
[question] best way to have my own reward model which is backed by rules 🏋 PPO Related to PPO ❓ question Seeking clarification or more information
#2518 opened Dec 24, 2024 by yananchen1989
8
Soft Actor-Critic (SAC) Trainer ✨ enhancement New feature or request
#2517 opened Dec 23, 2024 by AMindToThink
3 tasks
RLOO trainer epochs/steps/episodes calculations seems not to be working properly 🐛 bug Something isn't working 🏋 RLOO Related to RLOO
#2515 opened Dec 23, 2024 by dawidm
7 of 9 tasks
2
Checkpointing is failing with SFTTrainer PEFT LoRA on DeepSpeed Zero-3 🐛 bug Something isn't working ⚡ PEFT Related to PEFT 🏋 SFT Related to SFT
#2514 opened Dec 21, 2024 by SwayamInSync
7 of 9 tasks
1
Absence of ref_model_name in the file which located in docs/source/best_of_n.mdx
#2508 opened Dec 20, 2024 by aivolcano
7 of 9 tasks
2
DDPO checkpoint ú· 🐛 bug Something isn't working 🏋 DPPO Related to DDPO 🙋 help from community wanted Open invitation for community members to contribute ⏳ needs more info Additional information or clarification is required to proceed
#2505 opened Dec 20, 2024 by nguyenhoa-uit
5 of 9 tasks
3
Spectrum training support ✨ enhancement New feature or request 🏋 SFT Related to SFT
#2504 opened Dec 19, 2024 by ggbetz
2
【Question】Does DPO trainer support with FSDP?
#2500 opened Dec 18, 2024 by yingtongxiong
2
[bug] objective/entropy < 0 when using rlootrainer and ppotrainer 🙋 help from community wanted Open invitation for community members to contribute 🏋 PPO Related to PPO ❓ question Seeking clarification or more information 🏋 RLOO Related to RLOO
#2496 opened Dec 17, 2024 by macheng6
1
[Tracking issue] Integrate native liger-kernel losses ✨ enhancement New feature or request 🧒 good second issue Good for contributors with basic project familiarity
#2495 opened Dec 17, 2024 by qgallouedec
5 tasks
2
reward trainer section documentation section adding-a-margin-to-the-loss should mention about Llama3.1
#2493 opened Dec 17, 2024 by Kallinteris-Andreas
DeepSpeed with trl 🐛 bug Something isn't working 🚀 deepspeed Related to deepspeed 🏋 DPO Related to DPO ⏳ needs more info Additional information or clarification is required to proceed
#2490 opened Dec 16, 2024 by sagie-dekel
7 of 9 tasks
4
Main documentation instruction image needs a description
#2489 opened Dec 16, 2024 by Kallinteris-Andreas
RewardConfig's max_length argument docstring should indicate that it filters out dataset, rather than truncating it 📚 documentation Improvements or additions to documentation 👶 good first issue Good for newcomers 🙋 help from community wanted Open invitation for community members to contribute 🏋 Reward Related to Reward modelling
#2488 opened Dec 16, 2024 by Kallinteris-Andreas
1
UserWarning for train dpo with lora: None of the inputs have requires_grad=True. Gradients will be None
#2486 opened Dec 16, 2024 by xkw666
7 of 9 tasks
2
Trainer forces the use of a specific collator 🏋 GKD Related to GKD ❓ question Seeking clarification or more information
#2481 opened Dec 14, 2024 by hteague-qti
3
ProTip! Add no:assignee to see everything that’s not assigned.