issues
search
jasonvanf
/
llama-trl
LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA
Apache License 2.0
185
stars
23
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
What's the advantage of this library compare to the official TRL?
#7
disperaller
opened
3 months ago
1
多卡内存分配不均导致0号GPU内存溢出
#6
czx-li
opened
4 months ago
0
tuning_lm_with_rl.py does not appear to have a file named config.json
#5
judyhappy
opened
1 year ago
2
IndexError: index out of range in self on training_reward_model
#4
SeekPoint
opened
1 year ago
0
tuning_lm_with_rl 有完整运行成功的案例嘛？
#3
jerry1993-tech
opened
1 year ago
1
运行 train_llm_with_rl.py 是会在 ppo_trainer.generate(...) 报如下的错误，请教解决
#2
jerry1993-tech
opened
1 year ago
0
fix: AutoTokenizer
#1
dkqkxx
closed
1 year ago
1