llama.cpp/src/llama-sampling.h
wwoodsTM ff252ea48e
llama : add DRY sampler (#9702)
* sampling : add DRY sampler (post-refactor)

* DRY: Trying to fix coauthors, removed unneeded line

* DRY: Fixed redundant code

* DRY: Fixed crash issue due to DRY being in chain but uninitialized

---------

Co-authored-by: l3utterfly <gc.pthzfoldr@gmail.com>
Co-authored-by: pi6am <34464159+pi6am@users.noreply.github.com>
2024-10-25 19:07:34 +03:00

49 lines
1.5 KiB
C++

#pragma once
// TODO: rename llama-sampling.h/.cpp to llama-sampler.h/.cpp ?
#include "llama-grammar.h"
struct llama_vocab;
struct llama_grammar;
// sampler chain
struct llama_sampler_chain {
llama_sampler_chain_params params;
std::vector<struct llama_sampler *> samplers;
// timing
mutable int64_t t_sample_us;
mutable int32_t n_sample;
};
struct llama_sampler * llama_sampler_init_grammar_impl(
const struct llama_vocab & vocab,
const char * grammar_str,
const char * grammar_root);
struct llama_sampler * llama_sampler_init_infill_impl(
const struct llama_vocab & vocab);
struct llama_sampler * llama_sampler_init_dry_impl(
const struct llama_vocab & vocab,
int32_t context_size,
float dry_multiplier,
float dry_base,
int32_t dry_allowed_length,
int32_t dry_penalty_last_n,
const char ** seq_breakers,
size_t num_breakers);
struct llama_sampler * llama_sampler_init_dry_testing(
int32_t context_size,
float dry_multiplier,
float dry_base,
int32_t dry_allowed_length,
int32_t dry_penalty_last_n,
const std::vector<std::vector<llama_token>>& seq_breakers);