vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

examples: support LLaVA v1.5 (multimodal model) (#3436)

Browse source 
* 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>
This commit is contained in:
M. Yusuf Sarıgöz 2023-10-12 18:23:18 +03:00 • committed by GitHub
parent 9e24cc6e2e
commit 370359e5ba
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
15 changed files with 10214 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.h
View file

@ -104,6 +104,10 @@ struct gpt_params {
bool numa = false; // attempt optimizations that help on some NUMA systems
bool verbose_prompt = false; // print prompt tokens before generation
bool infill = false; // use infill mode
// multimodal models (see examples/llava)
std::string mmproj = ""; // path to multimodal projector
std::string image = ""; // path to an image file
};
bool gpt_params_parse(int argc, char ** argv, gpt_params & params);