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

llama : dynamic temperature sampling (#4972)

Browse source 
* implemented dynamic temperature sampling from koboldcpp

* removed trailing whitespace

* removed unused temp parameter in llama_sample_entropy

* exposed exponent_val in dynamic temp sampler

* added debug check for printf statements

* use nullptr in llama_sample_softmax call during llama_sample_entropy

this avoids counting the time taken stats twice

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* return earlier if there is only 1 candiate (i.e. max_entropy == 0)

* reformat 't' case in llama_sample_queue

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* check for one or zero candidates case in llama_sample_entropy

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
This commit is contained in:
l3utterfly 2024-01-26 05:06:22 +09:00 • committed by GitHub
parent d292f4f204
commit 5eaf9964fc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 88 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

12
common/sampling.cpp
View file

@ -129,6 +129,8 @@ static void sampler_queue(
const int n_vocab = llama_n_vocab(llama_get_model(ctx_main));
const float temp = params.temp;
const float dynatemp_range = params.dynatemp_range;
const float dynatemp_exponent = params.dynatemp_exponent;
const int32_t top_k = params.top_k <= 0 ? n_vocab : params.top_k;
const float top_p = params.top_p;
const float min_p = params.min_p;
@ -143,7 +145,15 @@ static void sampler_queue(
case 'y': llama_sample_typical (ctx_main, &cur_p, typical_p, min_keep); break;
case 'p': llama_sample_top_p (ctx_main, &cur_p, top_p, min_keep); break;
case 'm': llama_sample_min_p (ctx_main, &cur_p, min_p, min_keep); break;
case 't': llama_sample_temp (ctx_main, &cur_p, temp); break;
case 't':
if (dynatemp_range > 0) {
float dynatemp_min = std::max(0.0f, temp - dynatemp_range);
float dynatemp_max = std::max(0.0f, temp + dynatemp_range);
llama_sample_entropy(ctx_main, &cur_p, dynatemp_min, dynatemp_max, dynatemp_exponent);
} else {
llama_sample_temp(ctx_main, &cur_p, temp);
}
break;
default : break;
}
}