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

Merge branch 'master' into custom-attention-mask

Browse source
This commit is contained in:
Georgi Gerganov 2023-09-28 15:19:57 +03:00
commit 25856900db
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
36 changed files with 730 additions and 239 deletions
Download patch file Download diff file Expand all files Collapse all files

15
llama.h
View file

@ -66,12 +66,6 @@ extern "C" {
typedef int32_t llama_token;
typedef int32_t llama_seq_id;
enum llama_log_level {
LLAMA_LOG_LEVEL_ERROR = 2,
LLAMA_LOG_LEVEL_WARN = 3,
LLAMA_LOG_LEVEL_INFO = 4
};
enum llama_vocab_type {
LLAMA_VOCAB_TYPE_SPM = 0, // SentencePiece
LLAMA_VOCAB_TYPE_BPE = 1, // Byte Pair Encoding
@ -184,13 +178,6 @@ extern "C" {
bool embedding; // embedding mode only
};
// Signature for logging events
// Note that text includes the new line character at the end for most events.
// If your logging mechanism cannot handle that, check if the last character is '\n' and strip it
// if it exists.
// It might not exist for progress report where '.' is output repeatedly.
typedef void (*llama_log_callback)(enum llama_log_level level, const char * text, void * user_data);
// model quantization parameters
typedef struct llama_model_quantize_params {
int nthread; // number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency()
@ -729,7 +716,7 @@ extern "C" {
// Set callback for all future logging events.
// If this is not called, or NULL is supplied, everything is output on stderr.
LLAMA_API void llama_log_set(llama_log_callback log_callback, void * user_data);
LLAMA_API void llama_log_set(ggml_log_callback log_callback, void * user_data);
LLAMA_API void llama_dump_timing_info_yaml(FILE * stream, const struct llama_context * ctx);