diff options
| author | Damian Stewart <d@damianstewart.com> | 2023-11-06 22:36:23 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-11-07 00:36:23 +0300 |
| commit | 381efbf480959bb6d1e247a8b0c2328f22e350f8 (patch) | |
| tree | e6ad3f01c2b681b5af7300d0d5c8650fbfe1eeaa /examples/llava/README.md | |
| parent | 2833a6f63c1b87c7f4ac574bcf7a15a2f3bf3ede (diff) | |
llava : expose as a shared library for downstream projects (#3613)
* wip llava python bindings compatibility
* add external llava API
* add base64 in-prompt image support
* wip refactor image loading
* refactor image load out of llava init
* cleanup
* further cleanup; move llava-cli into its own file and rename
* move base64.hpp into common/
* collapse clip and llava libraries
* move llava into its own subdir
* wip
* fix bug where base64 string was not removed from the prompt
* get libllava to output in the right place
* expose llava methods in libllama.dylib
* cleanup memory usage around clip_image_*
* cleanup and refactor *again*
* update headerdoc
* build with cmake, not tested (WIP)
* Editorconfig
* Editorconfig
* Build with make
* Build with make
* Fix cyclical depts on Windows
* attempt to fix build on Windows
* attempt to fix build on Windows
* Upd TODOs
* attempt to fix build on Windows+CUDA
* Revert changes in cmake
* Fix according to review comments
* Support building as a shared library
* address review comments
---------
Co-authored-by: M. Yusuf Sarıgöz <yusufsarigoz@gmail.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
Diffstat (limited to 'examples/llava/README.md')
| -rw-r--r-- | examples/llava/README.md | 7 |
1 files changed, 3 insertions, 4 deletions
diff --git a/examples/llava/README.md b/examples/llava/README.md index fc3446b6..323c5fdd 100644 --- a/examples/llava/README.md +++ b/examples/llava/README.md @@ -9,12 +9,12 @@ models are available. After API is confirmed, more models will be supported / uploaded. ## Usage -Build with cmake or run `make llava` to build it. +Build with cmake or run `make llava-cli` to build it. -After building, run: `./llava` to see the usage. For example: +After building, run: `./llava-cli` to see the usage. For example: ```sh -./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 +./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. @@ -51,7 +51,6 @@ Now both the LLaMA part and the image encoder is in the `llava-v1.5-7b` director ## TODO -- [ ] Support server mode. - [ ] Support non-CPU backend for the image encoding part. - [ ] Support different sampling methods. - [ ] Support more model variants. |