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

llava : update readme a bit

Browse source
This commit is contained in:
Georgi Gerganov 2024-02-14 09:35:57 +02:00
parent 7974ff7f02
commit 6727cfd21a
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
examples/llava/README.md
View file

@ -19,9 +19,9 @@ After building, run: `./llava-cli` to see the usage. For example:
**note**: A lower temperature like 0.1 is recommended for better quality. add `--temp 0.1` to the command to do so.
## Model conversion
## LLaVA 1.5
- Clone `llava-v15-7b` and `clip-vit-large-patch14-336` locally:
- Clone a LLaVA and a CLIP model ([available options](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md)). For example:
```sh
git clone https://huggingface.co/liuhaotian/llava-v1.5-7b
@ -59,6 +59,8 @@ Now both the LLaMA part and the image encoder is in the `llava-v1.5-7b` director
- Use `llava-surgery-v2.py`
- TODO: add detailed instructions
## TODO
- [x] Support non-CPU backend for the image encoding part.