From 444dbce8880e9d80162bcd081b503c8eb32972de Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?M=2E=20Yusuf=20Sar=C4=B1g=C3=B6z?= Date: Mon, 9 Oct 2023 09:47:56 +0300 Subject: [PATCH] Add readme --- examples/llava/README.md | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 examples/llava/README.md diff --git a/examples/llava/README.md b/examples/llava/README.md new file mode 100644 index 000000000..fbb30b860 --- /dev/null +++ b/examples/llava/README.md @@ -0,0 +1,29 @@ +# LLaVA + +Currently this implementation supports [llava-v1.5](https://huggingface.co/liuhaotian/llava-v1.5-7b) variants. + +The pre-converted 7b model can be found [here](https://huggingface.co/mys/ggml_llava-v1.5-7b). + +After API is confirmed, more models will be supported / uploaded. +## Usage +The `llava` target is cmake-only for now (TODO: add to `make`) and built as a part of examples. + +After building, run: `./bin/llava` to see the usage. For example: + +```sh +./bin/llava path/to/llava-v1.5-7b/ggml-model-q5_k.gguf path/to/llava-v1.5-7b/mmproj-model-f16.gguf path/to/an/image.jpg +``` + +## TODO + +These will be include in this pr: + +- [ ] Better command line interface. +- [ ] Document model conversion. + +These will be another PR: + +- [ ] Support server mode. +- [ ] Support non-CPU backend for the image encoding part. +- [ ] Support different sampling methods. +- [ ] Support more model variants.