Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 13:58:46 +01:00
Code Issues Packages Projects Releases Wiki Activity

added ctx_size parameter (#148)

Browse Source 
* added ctx_size parameter

* added it in more places

* Apply suggestions from code review

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Justin Suess 2023-03-15 15:42:40 -04:00 committed by GitHub
parent 16b2c61a22
commit 2d64715ad4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
main.cpp
View File

@ -547,6 +547,8 @@ bool llama_eval(
const int d_key = n_embd/n_head;
// TODO: check if this size scales with n_ctx linearly and remove constant. somehow I feel it wasn't the case
// static size_t buf_size = hparams.n_ctx*1024*1024;
static size_t buf_size = 512u*1024*1024;
static void * buf = malloc(buf_size);
@ -819,8 +821,7 @@ int main(int argc, char ** argv) {
// load the model
{
const int64_t t_start_us = ggml_time_us();
if (!llama_model_load(params.model, model, vocab, 512)) { // TODO: set context from user input ??
if (!llama_model_load(params.model, model, vocab, params.n_ctx)) {
fprintf(stderr, "%s: failed to load model from '%s'\n", __func__, params.model.c_str());
return 1;
}

3
utils.cpp
View File

@ -37,6 +37,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
params.n_predict = std::stoi(argv[++i]);
} else if (arg == "--top_k") {
params.top_k = std::stoi(argv[++i]);
} else if (arg == "-c" || arg == "--ctx_size") {
params.n_ctx = std::stoi(argv[++i]);
} else if (arg == "--top_p") {
params.top_p = std::stof(argv[++i]);
} else if (arg == "--temp") {
@ -92,6 +94,7 @@ void gpt_print_usage(int argc, char ** argv, const gpt_params & params) {
fprintf(stderr, " --top_p N top-p sampling (default: %.1f)\n", params.top_p);
fprintf(stderr, " --repeat_last_n N last n tokens to consider for penalize (default: %d)\n", params.repeat_last_n);
fprintf(stderr, " --repeat_penalty N penalize repeat sequence of tokens (default: %.1f)\n", params.repeat_penalty);
fprintf(stderr, " -c N, --ctx_size N size of the prompt context (default: %d)\n", params.n_ctx);
fprintf(stderr, " --temp N temperature (default: %.1f)\n", params.temp);
fprintf(stderr, " -b N, --batch_size N batch size for prompt processing (default: %d)\n", params.n_batch);
fprintf(stderr, " -m FNAME, --model FNAME\n");

1
utils.h
View File

@ -17,6 +17,7 @@ struct gpt_params {
int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency());
int32_t n_predict = 128; // new tokens to predict
int32_t repeat_last_n = 64; // last n tokens to penalize
int32_t n_ctx = 512; //context size
// sampling parameters
int32_t top_k = 40;