initial sampling changes:

This commit is contained in:
VJHack 2025-01-09 23:04:28 -06:00
parent f7cd13301c
commit ddc3c2208a
3 changed files with 64 additions and 8 deletions

View file

@ -95,6 +95,7 @@ enum common_sampler_type {
COMMON_SAMPLER_TYPE_XTC = 8,
COMMON_SAMPLER_TYPE_INFILL = 9,
COMMON_SAMPLER_TYPE_PENALTIES = 10,
COMMON_SAMPLER_TYPE_TOP_N_SIGMA = 11
};
// dimensionality reduction methods, used by cvector-generator
@ -128,6 +129,7 @@ struct common_params_sampling {
int32_t dry_allowed_length = 2; // tokens extending repetitions beyond this receive penalty
int32_t dry_penalty_last_n = -1; // how many tokens to scan for repetitions (0 = disable penalty, -1 = context size)
int32_t mirostat = 0; // 0 = disabled, 1 = mirostat, 2 = mirostat 2.0
int32_t top_n_sigma = 2;
float mirostat_tau = 5.00f; // target entropy
float mirostat_eta = 0.10f; // learning rate
bool ignore_eos = false;
@ -146,6 +148,7 @@ struct common_params_sampling {
COMMON_SAMPLER_TYPE_MIN_P,
COMMON_SAMPLER_TYPE_XTC,
COMMON_SAMPLER_TYPE_TEMPERATURE,
COMMON_SAMPLER_TYPE_TOP_N_SIGMA,
};
std::string grammar; // optional BNF-like grammar to constrain sampling