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

Standardize 0.0 disabling min_p upon feedback

Browse source
This commit is contained in:
kalomaze 2023-10-28 23:12:14 -05:00
parent 62fc77153b
commit 49b68e8226
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.cpp
View file

@ -685,7 +685,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
printf(" --top-k N top-k sampling (default: %d, 0 = disabled)\n", sparams.top_k);
printf(" --top-p N top-p sampling (default: %.1f, 1.0 = disabled)\n", (double)sparams.top_p);
printf(" --min-p N min-p sampling (default: %.2f, 1.0 = disabled)\n", (double)sparams.min_p);
printf(" --min-p N min-p sampling (default: %.2f, 0.0 = disabled)\n", (double)sparams.min_p);
printf(" --tfs N tail free sampling, parameter z (default: %.1f, 1.0 = disabled)\n", (double)sparams.tfs_z);
printf(" --typical N locally typical sampling, parameter p (default: %.1f, 1.0 = disabled)\n", (double)sparams.typical_p);
printf(" --repeat-last-n N last n tokens to consider for penalize (default: %d, 0 = disabled, -1 = ctx_size)\n", sparams.penalty_last_n);
@ -1282,7 +1282,7 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l
fprintf(stream, "threads: %d # default: %d\n", params.n_threads, std::thread::hardware_concurrency());
fprintf(stream, "top_k: %d # default: 40\n", sparams.top_k);
fprintf(stream, "top_p: %f # default: 0.95\n", sparams.top_p);
fprintf(stream, "min_p: %f # default: 0.05\n", sparams.min_p);
fprintf(stream, "min_p: %f # default: 0.0\n", sparams.min_p);
fprintf(stream, "typical_p: %f # default: 1.0\n", sparams.typical_p);
fprintf(stream, "verbose_prompt: %s # default: false\n", params.verbose_prompt ? "true" : "false");
}

2
common/sampling.cpp
View file

@ -190,7 +190,7 @@ llama_token llama_sampling_sample(
llama_sample_top_k (ctx_main, &cur_p, top_k, min_keep);
llama_sample_tail_free(ctx_main, &cur_p, tfs_z, min_keep);
llama_sample_typical (ctx_main, &cur_p, typical_p, min_keep);
if (min_p != 1.0 && min_p != 0.0) {
if (min_p != 0.0) {
llama_sample_min_p(ctx_main, &cur_p, min_p, min_keep);
} else {
llama_sample_top_p(ctx_main, &cur_p, top_p, min_keep);