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

Starting point

Browse source
This commit is contained in:
kalomaze 2023-11-30 07:01:05 -06:00
parent 1f5cd83275
commit 23987729aa
1 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
common/sampling.cpp
View file

@ -187,13 +187,16 @@ llama_token llama_sampling_sample(
} else {
// temperature sampling
size_t min_keep = std::max(1, params.n_probs);
float output_temp = 1.0; // WIP, this should be defined separately as its own parameter.
llama_sample_temp (ctx_main, &cur_p, temp); // "Initial temp", this is how it's traditionally implemented
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);
llama_sample_top_p (ctx_main, &cur_p, top_p, min_keep);
llama_sample_min_p (ctx_main, &cur_p, min_p, min_keep);
llama_sample_temp (ctx_main, &cur_p, temp);
llama_sample_temp (ctx_main, &cur_p, temp_last); // "Output temp", this is how llama.cpp chose to implement it
id = llama_sample_token(ctx_main, &cur_p);