Skip to content

Issues: OpenRLHF/OpenRLHF

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

33 Open 256 Closed
33 Open 256 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

reward变为0
#517 opened Nov 12, 2024 by anoxia-1
1
PRM loss 疑问
#510 opened Nov 7, 2024 by EthanChen1234
3
DPO越训显存占用越大直到爆显存
#508 opened Nov 7, 2024 by Cerberous
2
请问支持对于多模态模型进行偏好训练吗？
#503 opened Nov 6, 2024 by bonre
1
assert state_dict_keys.issubset( [rank0]: AssertionError: mismatch keys
#501 opened Nov 5, 2024 by anoxia-1
1
如何使用多机多卡训练 70B PRM？
#500 opened Nov 5, 2024 by banksy23
1
Support for PPO for PRM? enhancement New feature or request
#498 opened Nov 1, 2024 by ljb121002
1
Qwen2-7B的输出用Qwen2-1.5B计算logp的时候报错
#496 opened Oct 31, 2024 by ZexuSun
1
请问支持 PPO 过程中使用 PRM 而不是 ORM 嘛？
#490 opened Oct 28, 2024 by banksy23
1
[RFC] Support SGLang generation in RLHF enhancement New feature or request
#487 opened Oct 28, 2024 by hijkzzz
1
How do you connect different models using Ray.
#472 opened Oct 22, 2024 by zpcalan
3
PPO training stuck for Llama-3.1
#470 opened Oct 21, 2024 by zhenghaoxu-gatech
1
Unnecessary logprob computation in actor.forward
#467 opened Oct 19, 2024 by zkshan2002
1
使用adam_offload后，训练完模型save_model时报错
#460 opened Oct 14, 2024 by pythonla
3
知识蒸馏结果复现
#456 opened Oct 7, 2024 by jinchenyu
@ifromeast
5
Lora merge error after dpo training with lora.
#436 opened Sep 11, 2024 by KaedinLian
3
Evaluate the PPO Process: Compatibility issues between DeepSpeed checkpoints and Transformers models
#426 opened Aug 20, 2024 by Ricardokevins
1
PPO训练overlap_comm打开会对训练表现造成很大影响
#423 opened Aug 20, 2024 by andylrx
1
DPO后的模型推理出的结果都是无序符号
#366 opened Jul 18, 2024 by 2024WY
3
A worker died or was killed while executing a task by an unexpected system error.
#360 opened Jul 15, 2024 by lusongshuo-mt
4
会不会支持异步生成训练 enhancement New feature or request
#353 opened Jul 11, 2024 by syx11237744
1
PPO加载完模型后卡在bundle_reservation_check_func这里
#331 opened Jun 24, 2024 by lixsh6
4
Generate function for distributional training
#324 opened Jun 8, 2024 by louieworth
2
可以增加支持SimPO吗
#311 opened May 29, 2024 by victorShawFan
3
使用Deepseek-lite训练DPO，显示expected mat1 and mat2 to have the same type, but got: float != c10: : BFLoat16
#306 opened May 27, 2024 by victorShawFan
3
ProTip! Follow long discussions with comments:>50.