tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-13 11:57:43 -04:00
Code Issues Packages Projects Releases Wiki Activity

Add back top_k (#56)

Browse Source 
* Add back top_k

* Update utils.cpp

* Update utils.h

---------

Co-authored-by: Bill Hamilton <bill.hamilton@shopify.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
beiller
2023-03-12 16:23:15 -04:00
committed by GitHub
parent eb062bb012
commit 02f0c6fe7f
3 changed files with 12 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
main.cpp
View File

@@ -825,6 +825,7 @@ int main(int argc, char ** argv) {
if (i >= embd_inp.size()) {
// sample next token
const float top_k = params.top_k;
const float top_p = params.top_p;
const float temp = params.temp;
const float repeat_penalty = params.repeat_penalty;
@@ -836,7 +837,7 @@ int main(int argc, char ** argv) {
{
const int64_t t_start_sample_us = ggml_time_us();
id = llama_sample_top_p(vocab, logits.data() + (logits.size() - n_vocab), last_n_tokens, repeat_penalty, top_p, temp, rng);
id = llama_sample_top_p_top_k(vocab, logits.data() + (logits.size() - n_vocab), last_n_tokens, repeat_penalty, top_k, top_p, temp, rng);
last_n_tokens.erase(last_n_tokens.begin());
last_n_tokens.push_back(id);