llama.cpp/examples/llava/llava.h
tc-mb 3071c0a5f2
llava : support MiniCPM-V-2.5 (#7599)
* init

* rename

* add run android for termux in readme

* add android readme

* add instructions in readme

* change name in readme

* Update README.md

* fixed line

* add result in readme

* random pos_embed

* add positions index

* change for ollama

* change for ollama

* better pos_embed in clip

* support ollama

* updata cmakelist

* updata cmakelist

* rename wrapper

* clear code

* replace and organize code

* add link

* sync master

* fix warnings

* fix warnings

* fix bug in bicubic resize when need resize iamge smaller

* receive review comments and modify

* receive review comments and modify

* put all code into llava dir

* fix quality problem in pr code

* change n_layer

* add space in "-1"

* imitate reshape bug of python code

* fix bug in clip

* fix issues for merging

* fix llama-minicpmv-cli in cmake file

* change pr readme

* fix code review

* remove in line 33 directory in the /cmakelists.txt (not in example, in the main dir

* fix cmakefile

* add warn

* fix KEY_HAS_MINICPMV_PROJ

* remove load_image_size into clip_ctx

* remove the extern "C", MINICPMV_API

* fix uhd code for review comment

* delete minicpmv-wrapper in pr

* remove uhd_image_embed

* Modify 2 notes

* clip : style changes

* del common.h in clip

* fix Type-Check error

* fix Type-Check error

* fix Type-Check error

* fix Type-Check error

* fix makefile error

* fix ubuntu-make error

* try fix clip

* try fix 1

---------

Co-authored-by: Hongji Zhu <fireyoucan@gmail.com>
Co-authored-by: harvestingmoon <leewenyeong@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-08-09 13:33:53 +03:00

50 lines
1.8 KiB
C

#ifndef LLAVA_H
#define LLAVA_H
#include "ggml.h"
#ifdef LLAMA_SHARED
# if defined(_WIN32) && !defined(__MINGW32__)
# ifdef LLAMA_BUILD
# define LLAVA_API __declspec(dllexport)
# else
# define LLAVA_API __declspec(dllimport)
# endif
# else
# define LLAVA_API __attribute__ ((visibility ("default")))
# endif
#else
# define LLAVA_API
#endif
#ifdef __cplusplus
extern "C" {
#endif
struct clip_ctx;
struct llava_image_embed {
float * embed;
int n_image_pos;
};
/** sanity check for clip <-> llava embed size match */
LLAVA_API bool llava_validate_embed_size(const struct llama_context * ctx_llama, const struct clip_ctx * ctx_clip);
LLAVA_API bool llava_image_embed_make_with_clip_img(struct clip_ctx * ctx_clip, int n_threads, const struct clip_image_u8 * img, float ** image_embd_out, int * n_img_pos_out);
/** build an image embed from image file bytes */
LLAVA_API struct llava_image_embed * llava_image_embed_make_with_bytes(struct clip_ctx * ctx_clip, int n_threads, const unsigned char * image_bytes, int image_bytes_length);
/** build an image embed from a path to an image filename */
LLAVA_API struct llava_image_embed * llava_image_embed_make_with_filename(struct clip_ctx * ctx_clip, int n_threads, const char * image_path);
/** free an embedding made with llava_image_embed_make_* */
LLAVA_API void llava_image_embed_free(struct llava_image_embed * embed);
/** write the image represented by embed into the llama context with batch size n_batch, starting at context pos n_past. on completion, n_past points to the next position in the context after the image embed. */
LLAVA_API bool llava_eval_image_embed(struct llama_context * ctx_llama, const struct llava_image_embed * embed, int n_batch, int * n_past);
#ifdef __cplusplus
}
#endif
#endif