mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-17 21:51:27 -04:00
main : add option to save full output to session (#1338)
* main : add option to save full output to session * split behavior into --session and --prompt-cache * restore original implementation with new names * PR comments * move the check for incompatible parameters to gpt_params_parse * Fix whitespace Co-authored-by: DannyDaemonic <DannyDaemonic@gmail.com> --------- Co-authored-by: DannyDaemonic <DannyDaemonic@gmail.com>
This commit is contained in:
@@ -46,9 +46,9 @@ struct gpt_params {
|
||||
|
||||
std::string model = "models/lamma-7B/ggml-model.bin"; // model path
|
||||
std::string prompt = "";
|
||||
std::string path_session = ""; // path to file for saving/loading model eval state
|
||||
std::string input_prefix = ""; // string to prefix user inputs with
|
||||
std::string input_suffix = ""; // string to suffix user inputs with
|
||||
std::string path_prompt_cache = ""; // path to file for saving/loading prompt eval state
|
||||
std::string input_prefix = ""; // string to prefix user inputs with
|
||||
std::string input_suffix = ""; // string to suffix user inputs with
|
||||
std::vector<std::string> antiprompt; // string upon seeing which more user input is prompted
|
||||
|
||||
std::string lora_adapter = ""; // lora adapter path
|
||||
@@ -58,6 +58,7 @@ struct gpt_params {
|
||||
bool random_prompt = false; // do not randomize prompt if none provided
|
||||
bool use_color = false; // use color to distinguish generations and inputs
|
||||
bool interactive = false; // interactive mode
|
||||
bool prompt_cache_all = false; // save user input and generations to prompt cache
|
||||
|
||||
bool embedding = false; // get only sentence embedding
|
||||
bool interactive_first = false; // wait for user input immediately
|
||||
|
Reference in New Issue
Block a user