mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-31 08:51:55 +00:00
aa23412989
* Create llava-survery-v2.py * Update convert-image-encoder-to-gguf.py * Update convert-image-encoder-to-gguf.py * Rename llava-survery-v2.py to llava-surgery-v2.py * Update convert-image-encoder-to-gguf.py will now search for projector * Update convert-image-encoder-to-gguf.py whoops * Update llava-surgery-v2.py * Clip: Bugfix for normalization (it did not loat the 3 std and mean values) Clip: bicubic resize function Clip: added save-to-bmp/pil for debugging and conversion from/to 32/8 images Clip: added normalization with FP16 precision simulation (image tensors match HF implementation, can be switched off, only used for llava-1.6) Clip: added newline tensor, mergetype kv, image-grid kv, new resize-pad function with resolution from gridpoints Clip: clip_image_preprocess now returns a float * vector instead of float, this way llava 1.5 and 1.6 is supported llava: added ggml cpu graph for embedding patching, added spatial_unpad preliminary support, added a lot of comments that need to be cleaned when all is final convert-image-encoder: fixed image-grid flattening * whitespace corrections * ws * Tensors are now properly permuted. Before the embeddings were inserted 1:1, now they are split into the 24x24 patches as in reference. * ws * added verbose_prompt support into cli added stopwords for llava-1.6 into cli * moved llava functions to llava.cpp, made clip.h C compatible API, replaced vector style functions with pointers, added a debug define to remove functions from compilation while not needed * ws * convert : skip unknown tensors (need for LLaVA) * llava : update readme * llava : fix compile warnings * llava : style * convert : add --skip-unknown CLI arg * server : remove clip structs * bugfix for non llava-1.6 It should now work with llava-1.5 as well * clip : minor code rearrange * llava : update readme a bit --------- Co-authored-by: John <cmt-nct@users.noreply.github.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
49 lines
1.6 KiB
C
49 lines
1.6 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
|
|
|
|
struct clip_ctx;
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
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 llama_context * ctx_llama, const clip_ctx * ctx_clip);
|
|
|
|
/** 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);
|
|
LLAVA_API void llava_image_embed_free(struct llava_image_embed * embed);
|
|
/** free an embedding made with llava_image_embed_make_* */
|
|
|
|
/** 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
|