sampling : rename penalty params + reduce size of "prev" vector

This commit is contained in:
Georgi Gerganov 2023-10-20 17:47:13 +03:00
parent 84ed48b473
commit b526561583
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
7 changed files with 86 additions and 79 deletions

View file

@ -10,17 +10,17 @@
// sampling parameters
typedef struct llama_sampling_params {
int32_t n_prev = 256; // number of previous tokens to remember
int32_t n_prev = 64; // number of previous tokens to remember
int32_t n_probs = 0; // if greater than 0, output the probabilities of top n_probs tokens.
int32_t top_k = 40; // <= 0 to use vocab size
float top_p = 0.95f; // 1.0 = disabled
float tfs_z = 1.00f; // 1.0 = disabled
float typical_p = 1.00f; // 1.0 = disabled
float temp = 0.80f; // 1.0 = disabled
float repeat_penalty = 1.10f; // 1.0 = disabled
int32_t repeat_last_n = 64; // last n tokens to penalize (0 = disable penalty, -1 = context size)
float frequency_penalty = 0.00f; // 0.0 = disabled
float presence_penalty = 0.00f; // 0.0 = disabled
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
float penalty_present = 0.00f; // 0.0 = disabled
int32_t mirostat = 0; // 0 = disabled, 1 = mirostat, 2 = mirostat 2.0
float mirostat_tau = 5.00f; // target entropy
float mirostat_eta = 0.10f; // learning rate
@ -34,7 +34,6 @@ typedef struct llama_sampling_params {
float cfg_scale = 1.f; // How strong is guidance
std::unordered_map<llama_token, float> logit_bias; // logit bias for specific tokens
} llama_sampling_params;
// general sampler context