tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-26 10:09:41 -04:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix compile warnings

Browse Source
This commit is contained in:
Georgi Gerganov
2023-05-02 23:09:08 +03:00
parent 5d5817ca60
commit 0e6cbff1b7
4 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llama.h
View File

@@ -192,10 +192,10 @@ extern "C" {
// Sampling functions
/// @details Repetition penalty described in CTRL academic paper https://arxiv.org/abs/1909.05858, with negative logit fix.
LLAMA_API void llama_sample_repetition_penalty(struct llama_context * ctx, llama_token_data_array * candidates, llama_token * last_tokens, size_t last_tokens_size, float penalty);
LLAMA_API void llama_sample_repetition_penalty(struct llama_context * ctx, llama_token_data_array * candidates, const llama_token * last_tokens, size_t last_tokens_size, float penalty);
/// @details Frequency and presence penalties described in OpenAI API https://platform.openai.com/docs/api-reference/parameter-details.
LLAMA_API void llama_sample_frequency_and_presence_penalties(struct llama_context * ctx, llama_token_data_array * candidates, llama_token * last_tokens, size_t last_tokens_size, float alpha_frequency, float alpha_presence);
LLAMA_API void llama_sample_frequency_and_presence_penalties(struct llama_context * ctx, llama_token_data_array * candidates, const llama_token * last_tokens, size_t last_tokens_size, float alpha_frequency, float alpha_presence);
/// @details Sorts candidate tokens by their logits in descending order and calculate probabilities based on logits.
LLAMA_API void llama_sample_softmax(struct llama_context * ctx, llama_token_data_array * candidates);