mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Generalize multimodality (llava/minigpt4 7b and 13b now supported) (#1741)

Browse source
This commit is contained in:
Wojtab 2023-05-10 01:18:02 +02:00 • committed by GitHub
parent a2b25322f0
commit e9e75a9ec7
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
22 changed files with 812 additions and 371 deletions
Download patch file Download diff file Expand all files Collapse all files

9
extensions/multimodal/pipelines/llava/README.md Normal file
View file

@ -0,0 +1,9 @@
## LLaVA pipeline
This module provides 2 pipelines:
- `llava-7b` - for use with LLaVA v0 7B model (finetuned LLaMa 7B)
- `llava-13b` - for use with LLaVA v0 13B model (finetuned LLaMa 13B)
[LLaVA](https://github.com/haotian-liu/LLaVA) uses CLIP `openai/clip-vit-large-patch14` as the vision model, and then a single linear layer. For 13B the projector weights are in `liuhaotian/LLaVA-13b-delta-v0`, and for 7B they are in `liuhaotian/LLaVA-7b-delta-v0`.
The supported parameter combinations for both the vision model, and the projector are: CUDA/32bit, CUDA/16bit, CPU/32bit