diff options
| author | l3utterfly <gc.pthzfoldr@gmail.com> | 2024-01-26 05:06:22 +0900 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-01-25 22:06:22 +0200 |
| commit | 5eaf9964fc797d4585c214db32a463d557f3ed33 (patch) | |
| tree | e41be4957a366e1210769298156de9f09b9593c8 /common/sampling.h | |
| parent | d292f4f2047963f558dd516f1baaa71793e9acf2 (diff) | |
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>
Diffstat (limited to 'common/sampling.h')
| -rw-r--r-- | common/sampling.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/common/sampling.h b/common/sampling.h index 2ee18037..88899c09 100644 --- a/common/sampling.h +++ b/common/sampling.h @@ -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 |