CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-09 10:17:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : move sampling code into llama-sampling

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2024-07-19 18:15:36 +03:00
parent 081fe431aa
commit 0ddc8e361c
7 changed files with 758 additions and 699 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
include/llama.h
View File

@@ -1084,12 +1084,6 @@ extern "C" {
llama_token_data_array * candidates,
float temp);
/// @details Apply constraints from grammar
LLAMA_API void llama_sample_grammar(
struct llama_context * ctx,
llama_token_data_array * candidates,
const struct llama_grammar * grammar);
/// @details Mirostat 1.0 algorithm described in the paper https://arxiv.org/abs/2007.14966. Uses tokens instead of words.
/// @param candidates A vector of `llama_token_data` containing the candidate tokens, their probabilities (p), and log-odds (logit) for the current position in the generated text.
/// @param tau The target cross-entropy (or surprise) value you want to achieve for the generated text. A higher value corresponds to more surprising or less predictable text, while a lower value corresponds to less surprising or more predictable text.
@@ -1127,6 +1121,12 @@ extern "C" {
struct llama_context * ctx,
llama_token_data_array * candidates);
/// @details Apply constraints from grammar
LLAMA_API void llama_sample_grammar(
struct llama_context * ctx,
llama_token_data_array * candidates,
const struct llama_grammar * grammar);
/// @details Accepts the sampled token into the grammar
LLAMA_API void llama_grammar_accept_token(
struct llama_context * ctx,