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

added ctx_size parameter

Browse source
This commit is contained in:
Justin 2023-03-15 01:47:51 +00:00
parent 47857e564c
commit e3d780d833
3 changed files with 6 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

3
main.cpp
View file

@ -818,8 +818,7 @@ 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;
}

5
utils.cpp
View file

@ -37,7 +37,9 @@ 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 == "--top_p") {
} 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") {
params.temp = std::stof(argv[++i]);
@ -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");

2
utils.h
View file

@ -17,7 +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;
float top_p = 0.95f;