ilotoki_thu
/
alpaca_lora_4bit
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update README.md

This commit is contained in:
John Smith 2023-04-20 09:57:18 +08:00 committed by GitHub
parent 3b18aa1cc6
commit a0a0962de7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -17,8 +17,12 @@ It's fast on a 3070 Ti mobile. Uses 5-6 GB of GPU RAM.
![](alpaca_lora_4bit_penguin_fact.gif) ![](alpaca_lora_4bit_penguin_fact.gif)
# Development # Development
* Install Manual by s4rduk4r: https://github.com/s4rduk4r/alpaca_lora_4bit_readme/blob/main/README.md (**NOTE:** don't use the install script, use the requirements.txt instead.) * Install Manual by s4rduk4r: https://github.com/s4rduk4r/alpaca_lora_4bit_readme/blob/main/README.md
* Also Remember to create a venv if you do not want the packages be overwritten. * Also Remember to create a venv if you do not want the packages be overwritten.
* For those who want to use pip installable version:
```
pip install git+https://github.com/johnsmith0031/alpaca_lora_4bit@winglian-setup_pip
```
# Update Logs # Update Logs
* Resolved numerically unstable issue * Resolved numerically unstable issue
@ -36,6 +40,8 @@ It's fast on a 3070 Ti mobile. Uses 5-6 GB of GPU RAM.
* Added g_idx support in cuda backend (need recompile cuda kernel) * Added g_idx support in cuda backend (need recompile cuda kernel)
* Added xformers support * Added xformers support
* Removed triton, flash-atten from requirements.txt for compatibility * Removed triton, flash-atten from requirements.txt for compatibility
* Removed bitsandbytes from requirements
* Added pip installable branch based on winglian's PR
# Requirements # Requirements
gptq-for-llama <br> gptq-for-llama <br>