zetavg/LLaMA-LoRA-Tuner
UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models.
Python
Pinned issues
Issues
- 0
TypeError: __init__() got an unexpected keyword argument 'llm_int8_skip_modules'
#43 opened by AlexeiKaDev - 2
Private Repo can't load
#42 opened by sengiv - 0
Run pretrained model
#41 opened by xagler - 0
LlamaTokenizer class issue
#40 opened by SJayYangNN - 0
WandB charts lose data.
#39 opened by xzuyn - 0
WandB logging doesn't save evaluation loss
#38 opened by xzuyn - 0
Loss chart errors after a bit
#37 opened by xzuyn - 1
- 0
offload-between-cpu-and-gpu
#35 opened by seanychen - 1
- 0
Error when fine tuning: Size Mismatch
#33 opened by Lev-Stambler - 0
Executing tuned Model locally
#32 opened by muni-wobo - 1
QLora support
#27 opened by lighteternal - 0
Falcon Support
#30 opened by acadaiaca - 1
- 2
Support for Larger Models
#3 opened by scblaze - 10
- 0
Continue from checkpoint fails
#25 opened by LimLims - 3
Running locally without git and intternet
#19 opened by im50889 - 3
Can't use secondary Google drive
#16 opened by l0rinc - 3
Comparison to text-generation-webui
#18 opened by l0rinc - 2
Inference got error "probability tensor contains either `inf`, `nan` or element < 0" while using beams=2 with temperature=0.1
#5 opened by zetavg - 3
Aborting training should delete output folder
#12 opened by l0rinc - 2
Cannot select `None` template
#11 opened by l0rinc - 3
Refresh instead of timing out
#15 opened by l0rinc - 2
Support smaller models
#17 opened by l0rinc - 3
Syntax error in code from local install
#13 opened by joshnajera - 1
Type Issue on Google Colab
#9 opened by scblaze - 2
- 5
- 1
ValueError('Loading ... requires you to execute the tokenizer file in that repo on your local machine. Make sure you have read the code there to avoid malicious use, then set the option `trust_remote_code=True` to remove this error.')
#6 opened by zetavg - 3
Error When Fine Tuning
#2 opened by scblaze