mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-06-29 20:45:04 +00:00
server : allow to specify custom prompt for penalty calculation (#3727)
This commit is contained in:
@ -36,6 +36,9 @@ 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
|
||||
|
||||
std::vector<llama_token> penalty_prompt_tokens;
|
||||
bool use_penalty_prompt_tokens = false;
|
||||
} llama_sampling_params;
|
||||
|
||||
// general sampler context
|
||||
|
Reference in New Issue
Block a user