vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Final touches

Browse source
This commit is contained in:
Georgi Gerganov 2023-03-10 21:50:46 +02:00
parent 775328064e
commit 319cdb3e1f
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
5 changed files with 32 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

3
README.md
View file

@ -114,6 +114,5 @@ python3 convert-pth-to-ggml.py models/7B/ 1
In general, it seems to work, but I think it fails for unicode character support. Hopefully, someone can help with that
- I don't know yet how much the quantization affects the quality of the generated text
- Probably the token sampling can be improved
- No Windows support
- x86 quantization support [not yet ready](https://github.com/ggerganov/ggml/pull/27). Basically, you want to run this on Apple Silicon