wassname/alpaca_convert
1
0
Fork 0
mirror of https://github.com/wassname/alpaca_convert.git synced 2026-06-27 16:14:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
John Smith
2023-04-09 12:50:49 +08:00
committed by GitHub
parent 4c18a56fc0
commit f185b90c3e
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1
View File
@@ -33,6 +33,7 @@ It's fast on a 3070 Ti mobile. Uses 5-6 GB of GPU RAM.
* Added monkey patch for text generation webui for fixing initial eos token issue.
* Added Flash attention support. (Use --flash-attention)
* Added Triton backend to support model using groupsize and act-order. (Use --backend=triton)
* Added g_idx support in cuda backend (need recompile cuda kernel)
# Requirements
gptq-for-llama <br>