Skip to content

keep the minimum min_keep value to 1 in sampling #9603

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

keep the minimum min_keep value to 1 in sampling #9603

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 5 additions & 4 deletions common/sampling.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,22 +173,23 @@ struct gpt_sampler * gpt_sampler_init(const struct llama_model * model, const st

if (params.temp > 0.0f) {
if (params.mirostat == 0) {
size_t min_keep = std::max(1, params.min_keep);
for (const auto & cnstr : params.samplers) {
switch (cnstr) {
case GPT_SAMPLER_TYPE_TOP_K:
llama_sampler_chain_add(result->chain, llama_sampler_init_top_k (params.top_k));
break;
case GPT_SAMPLER_TYPE_TOP_P:
llama_sampler_chain_add(result->chain, llama_sampler_init_top_p (params.top_p, params.min_keep));
llama_sampler_chain_add(result->chain, llama_sampler_init_top_p (params.top_p, min_keep));
break;
case GPT_SAMPLER_TYPE_MIN_P:
llama_sampler_chain_add(result->chain, llama_sampler_init_min_p (params.min_p, params.min_keep));
llama_sampler_chain_add(result->chain, llama_sampler_init_min_p (params.min_p, min_keep));
break;
case GPT_SAMPLER_TYPE_TFS_Z:
llama_sampler_chain_add(result->chain, llama_sampler_init_tail_free(params.tfs_z, params.min_keep));
llama_sampler_chain_add(result->chain, llama_sampler_init_tail_free(params.tfs_z, min_keep));
break;
case GPT_SAMPLER_TYPE_TYPICAL_P:
llama_sampler_chain_add(result->chain, llama_sampler_init_typical (params.typ_p, params.min_keep));
llama_sampler_chain_add(result->chain, llama_sampler_init_typical (params.typ_p, min_keep));
break;
case GPT_SAMPLER_TYPE_TEMPERATURE:
llama_sampler_chain_add(result->chain, llama_sampler_init_temp_ext (params.temp, params.dynatemp_range, params.dynatemp_exponent));
Expand Down
Loading