Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / jackaduma/Vicuna-LoRA-RLHF-PyTorch issues and pull requests
#17 - changes and setup
Pull Request -
State: open - Opened by Ekanshjain55 6 months ago
#16 - any plans for adding repo using stable vicuna for conversation .. human: assistant
Issue -
State: open - Opened by andysingal about 1 year ago
#15 - how to evaluate?
Issue -
State: open - Opened by XuanRen4470 over 1 year ago
#14 - unable to merge reward adapter into model
Issue -
State: open - Opened by XuanRen4470 over 1 year ago
#12 - Can we another format than alpaca-instruct like alpaca-chat instruct format if yes how ?
Issue -
State: open - Opened by Tejaswi-kashyap-006 over 1 year ago
#11 - SFT with large loss {'loss': 388082722196684.8, 'learning_rate': 0.0, 'epoch': 0.02}
Issue -
State: open - Opened by LeiShenVictoria over 1 year ago
#10 - supervised_finetune.py failed with a wordaround
Issue -
State: open - Opened by SeekPoint over 1 year ago
- 1 comment
#9 - python train_reward_model.py failed
Issue -
State: open - Opened by SeekPoint over 1 year ago
#8 - 请问如何在training reward model中自定义数据集
Issue -
State: open - Opened by authurlord over 1 year ago
#7 - 不能理解为什么注释这行代码?
Issue -
State: open - Opened by apachemycat over 1 year ago
#6 - CUDA out of memory
Issue -
State: open - Opened by integrum-aiktuck over 1 year ago
#5 - Unable to merge reward adapter into model
Issue -
State: open - Opened by DavidFarago over 1 year ago
- 2 comments
#4 - What is the data format to LoRA-fine-tune Vicuna?
Issue -
State: open - Opened by DavidFarago over 1 year ago
#3 - 大神和原版vicuna仓库对比过效果吗?
Issue -
State: open - Opened by magneter over 1 year ago
- 1 comment
#2 - 跑最后一步报这个警告,要怎么改超参数呢
Issue -
State: open - Opened by greatheart1000 over 1 year ago
- 3 comments
#1 - Does it really work ob RTX2080Ti ?
Issue -
State: open - Opened by GuofaHuang over 1 year ago
- 1 comment