From 370359e5baf619f3a8d461023143d1494b1e8fde Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?M=2E=20Yusuf=20Sar=C4=B1g=C3=B6z?= Date: Thu, 12 Oct 2023 18:23:18 +0300 Subject: examples: support LLaVA v1.5 (multimodal model) (#3436) * 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 --- common/common.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'common/common.h') diff --git a/common/common.h b/common/common.h index fa115536..36fd4416 100644 --- a/common/common.h +++ b/common/common.h @@ -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); -- cgit v1.2.3