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

Update README.md

Browse Source
This commit is contained in:
John Smith
2023-03-21 16:49:08 +08:00
committed by GitHub
parent 8d198e0171
commit 3be75bb3db
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -3,7 +3,7 @@ Made some adjust for the code in peft and gptq for llama, and make it possible f
<br> <br>
~Still numerically unstable.~ Resolved. ~Still numerically unstable.~ Resolved.
<br> <br>
Reconstruct fp16 matrix from 4bit data and call torch.matmul drastically increased the inference speed. Reconstruct fp16 matrix from 4bit data and call torch.matmul largely increased the inference speed.
<br> <br>
# Requirements # Requirements
gptq-for-llama: https://github.com/qwopqwop200/GPTQ-for-LLaMa<br> gptq-for-llama: https://github.com/qwopqwop200/GPTQ-for-LLaMa<br>