|
|
@ -18,26 +18,25 @@ struct gpt_params {
|
|
|
|
int32_t n_predict = 128; // new tokens to predict
|
|
|
|
int32_t n_predict = 128; // new tokens to predict
|
|
|
|
int32_t repeat_last_n = 64; // last n tokens to penalize
|
|
|
|
int32_t repeat_last_n = 64; // last n tokens to penalize
|
|
|
|
int32_t n_ctx = 512; //context size
|
|
|
|
int32_t n_ctx = 512; //context size
|
|
|
|
bool memory_f16 = false; // use f16 instead of f32 for memory kv
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
// sampling parameters
|
|
|
|
// sampling parameters
|
|
|
|
int32_t top_k = 40;
|
|
|
|
int32_t top_k = 40;
|
|
|
|
float top_p = 0.95f;
|
|
|
|
float top_p = 0.95f;
|
|
|
|
float temp = 0.80f;
|
|
|
|
float temp = 0.80f;
|
|
|
|
float repeat_penalty = 1.30f;
|
|
|
|
float repeat_penalty = 1.10f;
|
|
|
|
|
|
|
|
|
|
|
|
int32_t n_batch = 8; // batch size for prompt processing
|
|
|
|
int32_t n_batch = 8; // batch size for prompt processing
|
|
|
|
|
|
|
|
|
|
|
|
std::string model = "models/lamma-7B/ggml-model.bin"; // model path
|
|
|
|
std::string model = "models/lamma-7B/ggml-model.bin"; // model path
|
|
|
|
std::string prompt = "";
|
|
|
|
std::string prompt = "";
|
|
|
|
|
|
|
|
|
|
|
|
bool random_prompt = false;
|
|
|
|
std::vector<std::string> antiprompt; // string upon seeing which more user input is prompted
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
bool memory_f16 = false; // use f16 instead of f32 for memory kv
|
|
|
|
|
|
|
|
bool random_prompt = false; // do not randomize prompt if none provided
|
|
|
|
bool use_color = false; // use color to distinguish generations and inputs
|
|
|
|
bool use_color = false; // use color to distinguish generations and inputs
|
|
|
|
|
|
|
|
|
|
|
|
bool interactive = false; // interactive mode
|
|
|
|
bool interactive = false; // interactive mode
|
|
|
|
bool interactive_start = false; // reverse prompt immediately
|
|
|
|
bool interactive_start = false; // reverse prompt immediately
|
|
|
|
std::vector<std::string> antiprompt; // string upon seeing which more user input is prompted
|
|
|
|
|
|
|
|
bool instruct = false; // instruction mode (used for Alpaca models)
|
|
|
|
bool instruct = false; // instruction mode (used for Alpaca models)
|
|
|
|
bool ignore_eos = false; // do not stop generating after eos
|
|
|
|
bool ignore_eos = false; // do not stop generating after eos
|
|
|
|
};
|
|
|
|
};
|
|
|
|