wassname/alpaca_convert
1
0
Fork 0
mirror of https://github.com/wassname/alpaca_convert.git synced 2026-06-27 17:47:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
John Smith
2023-03-20 15:04:18 +08:00
committed by GitHub
parent 04f5575a23
commit 5c1411ff18
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -1,7 +1,7 @@
# Alpaca Lora 4bit
Made some adjust for the code in peft and gptq for llama, and make it possible for lora finetuning with a 4 bits base model. The same adjustment can be made for 2, 3 and 8 bits.
<br>
Still numerically unstable.
~Still numerically unstable.~ Resolved.
<br>
# Requirements
gptq-for-llama: https://github.com/qwopqwop200/GPTQ-for-LLaMa<br>