llama : dynamic temperature sampling (#4972)
* 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:
parent
d292f4f204
commit
5eaf9964fc
4 changed files with 88 additions and 1 deletions
|
@ -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;
|
||||
}
|
||||
}
|
||||
|
|
|
@ -18,6 +18,8 @@ typedef struct llama_sampling_params {
|
|||
float tfs_z = 1.00f; // 1.0 = disabled
|
||||
float typical_p = 1.00f; // 1.0 = disabled
|
||||
float temp = 0.80f; // <= 0.0 to sample greedily, 0.0 to not output probabilities
|
||||
float dynatemp_range = 0.00f; // 0.0 = disabled
|
||||
float dynatemp_exponent = 1.00f; // controls how entropy maps to temperature in dynamic temperature sampler
|
||||
int32_t penalty_last_n = 64; // last n tokens to penalize (0 = disable penalty, -1 = context size)
|
||||
float penalty_repeat = 1.10f; // 1.0 = disabled
|
||||
float penalty_freq = 0.00f; // 0.0 = disabled
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue