Mirrors
/
EveryDream2trainer
mirror of https://github.com/victorchall/EveryDream2trainer.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

add doc item for xtuner llava

This commit is contained in:
Victor Hall 2024-05-04 22:37:05 -04:00
parent fb1caf52a7
commit 3d02fa146d
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
doc/CAPTION_COG.md
View File

@ -8,6 +8,14 @@ It is capable of naming and identifying things with proper nouns and has a large
<a href="https://colab.research.google.com/github/nawnie/EveryDream2trainer/blob/main/CaptionCog.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
## Llava update
This script now (confusiningly) supports (Xtuner's Llava Llama3 8b v1.1)[https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-transformers/tree/main].
To use, add `--model "https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-transformers/tree/main"` to your command line.
This is a work in progress. So far it seems bad_words do not work.
## Basics
Run `python caption_cog.py --help` to get a list of options.