370359e5ba
* WIP: start implementing LLaVA * rm scratch buf for now, will revert after cleanup * LLaVA image encoder is working. will combine with llama * Add llava inference code, but it's buggy. debugging * LLaVA is working e2e, needs to optimize memory allocation + cleanup * Use ggml_allocr + rm unnecessary code * fix: crlf -> lf * fix: new line at EoF * fix: trailing whitespace * Add readme * Update readme * Some cleanup * Are you happy editorconfig? * rm unused batch image preprocessing * rm unused import * fix: rm designated initializers * introduce pad-to-square mode for non-square images * are you happy editorconfig? * gitignore /llava * Handle cases where image file does not exist * add llava target to Makefile * add support for 13b model variant * Maybe seed is unlucky? * Check if apples are compared to apples * are you happy editorconfig? * Use temperature = 0.1 by default * command line: use gpt_params_parse() * minor * handle default n_predict * fix typo * llava : code formatting, rename files, fix compile warnings * do not use Wno-cast-qual for MSVC --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> |
||
|---|---|---|
| .. | ||
| clip.cpp | ||
| clip.h | ||
| CMakeLists.txt | ||
| convert-image-encoder-to-gguf.py | ||
| llava-surgery.py | ||
| llava-utils.h | ||
| llava.cpp | ||
| 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 to build it.
After building, run: ./llava to see the usage. For example:
./llava -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`` andclip-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
- Use
llava-surgery.pyto split the LLaVA model to LLaMA and multimodel projector constituents:
python ./examples/llava/llava-surgery.py -m ../llava-v1.5-7b
- Use
convert-image-encoder-to-gguf.pyto 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
- Use
convert.pyto 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 server mode.
- Support non-CPU backend for the image encoding part.
- Support different sampling methods.
- Support more model variants.