issues
search
jackaduma
/
Vicuna-LoRA-RLHF-PyTorch
A full pipeline to finetune Vicuna LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the Vicuna architecture. Basically ChatGPT but with Vicuna
MIT License
208
stars
18
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
changes and setup
#17
Ekanshjain55
opened
6 months ago
0
any plans for adding repo using stable vicuna for conversation .. human: assistant
#16
andysingal
opened
1 year ago
0
how to evaluate?
#15
XuanRen4470
opened
1 year ago
0
unable to merge reward adapter into model
#14
XuanRen4470
opened
1 year ago
0
Can we another format than alpaca-instruct like alpaca-chat instruct format if yes how ?
#12
Tejaswi-kashyap-006
opened
1 year ago
0
SFT with large loss {'loss': 388082722196684.8, 'learning_rate': 0.0, 'epoch': 0.02}
#11
LeiShenVictoria
opened
1 year ago
0
supervised_finetune.py failed with a wordaround
#10
SeekPoint
opened
1 year ago
1
python train_reward_model.py failed
#9
SeekPoint
opened
1 year ago
0
请问如何在training reward model中自定义数据集
#8
authurlord
opened
1 year ago
0
不能理解为什么注释这行代码?
#7
apachemycat
opened
1 year ago
0
CUDA out of memory
#6
integrum-aiktuck
opened
1 year ago
0
Unable to merge reward adapter into model
#5
DavidFarago
opened
1 year ago
2
What is the data format to LoRA-fine-tune Vicuna?
#4
DavidFarago
opened
1 year ago
0
大神和原版vicuna仓库对比过效果吗?
#3
magneter
opened
1 year ago
1
跑最后一步报这个警告,要怎么改超参数呢
#2
greatheart1000
opened
1 year ago
3
Does it really work ob RTX2080Ti ?
#1
GuofaHuang
opened
1 year ago
1