matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-12 08:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

client updates

Browse Source
This commit is contained in:
Jeffrey Morgan
2023-07-04 00:47:00 -04:00
parent 6292f4b64c
commit fd962a36e5
21 changed files with 198 additions and 3137 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
llama/binding/binding.h
View File

@@ -30,22 +30,13 @@ extern "C" {
extern unsigned char tokenCallback(void *, char *);
int load_state(void *ctx, char *statefile, char *modes);
int eval(void *params_ptr, void *ctx, char *text);
void save_state(void *ctx, char *dst, char *modes);
int eval(void *p, void *c, char *text);
void *load_model(const char *fname, int n_ctx, int n_seed, bool memory_f16,
bool mlock, bool embeddings, bool mmap, bool low_vram,
bool vocab_only, int n_gpu, int n_batch, const char *maingpu,
const char *tensorsplit, bool numa);
int get_embeddings(void *params_ptr, void *state_pr, float *res_embeddings);
int get_token_embeddings(void *params_ptr, void *state_pr, int *tokens,
int tokenSize, float *res_embeddings);
void *llama_allocate_params(
const char *prompt, int seed, int threads, int tokens, int top_k,
float top_p, float temp, float repeat_penalty, int repeat_last_n,
@@ -59,13 +50,11 @@ void *llama_allocate_params(
void llama_free_params(void *params_ptr);
void llama_binding_free_model(void *state);
void llama_binding_free_model(void *ctx);
int llama_predict(void *params_ptr, void *state_pr, char *result, bool debug);
#ifdef __cplusplus
}
std::vector<std::string> create_vector(const char **strings, int count);
void delete_vector(std::vector<std::string> *vec);
#endif