root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-14 14:59:52 +00:00
Code Issues Actions 14 Packages Projects Releases Wiki Activity
7cd0d3232f
llama.cpp/examples/llava
History
John 33c9892af5
llava : ShareGPT4V compatibility (vision encoder only loading) (#4172) 
* ShareGPT4 compatibility (vision encoder only loading)

Load only a CLIP vision encoder (as supplied by ShareGPT finetunes)
Corrects the argument parsing for --img_mean and --img_std (which were previously not parsed but attempted to access)
Defines defaults for img_mean and img_std which are equal to the llava 1.5 CLIP encoder, so you do not have to provide them

* Update convert-image-encoder-to-gguf.py
2023-11-30 23:11:14 +01:00
..
clip.cpp llava : fix regression for square images in #3613 (#4056) 2023-11-13 18:20:52 +03:00
clip.h llava : expose as a shared library for downstream projects (#3613) 2023-11-07 00:36:23 +03:00
CMakeLists.txt llava : expose as a shared library for downstream projects (#3613) 2023-11-07 00:36:23 +03:00
convert-image-encoder-to-gguf.py llava : ShareGPT4V compatibility (vision encoder only loading) (#4172) 2023-11-30 23:11:14 +01:00
llava-cli.cpp Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040) 2023-11-16 19:14:37 -07:00
llava-surgery.py multimodal : add BakLLaVA conversion support (#3682) 2023-10-19 19:40:41 +03:00
llava.cpp llava : fix compilation warning that fread return value is not used (#4069) 2023-11-17 17:22:56 +02:00
llava.h llava : expose as a shared library for downstream projects (#3613) 2023-11-07 00:36:23 +03:00
README.md llava : expose as a shared library for downstream projects (#3613) 2023-11-07 00:36:23 +03:00

README.md

LLaVA

Currently this implementation supports llava-v1.5 variants.

The pre-converted 7b and 13b models are available.

After API is confirmed, more models will be supported / uploaded.

Usage

Build with cmake or run make llava-cli to build it.

After building, run: ./llava-cli to see the usage. For example:

./llava-cli -m llava-v1.5-7b/ggml-model-q5_k.gguf --mmproj llava-v1.5-7b/mmproj-model-f16.gguf --image path/to/an/image.jpg

note: A lower temperature like 0.1 is recommended for better quality. add --temp 0.1 to the command to do so.

Model conversion

  • Clone llava-v15-7b`` and clip-vit-large-patch14-336`` locally:
git clone https://huggingface.co/liuhaotian/llava-v1.5-7b

git clone https://huggingface.co/openai/clip-vit-large-patch14-336
  1. Use llava-surgery.py to split the LLaVA model to LLaMA and multimodel projector constituents:
python ./examples/llava/llava-surgery.py -m ../llava-v1.5-7b
  1. Use convert-image-encoder-to-gguf.py to convert the LLaVA image encoder to GGUF:
python ./examples/llava/convert-image-encoder-to-gguf -m ../clip-vit-large-patch14-336 --llava-projector ../llava-v1.5-7b/llava.projector --output-dir ../llava-v1.5-7b
  1. Use convert.py to convert the LLaMA part of LLaVA to GGUF:
python ./convert.py ../llava-v1.5-7b

Now both the LLaMA part and the image encoder is in the llava-v1.5-7b directory.

TODO

  • Support non-CPU backend for the image encoding part.
  • Support different sampling methods.
  • Support more model variants.