vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

sampling : refactor init to use llama_sampling_params

Browse source
This commit is contained in:
Georgi Gerganov 2023-10-20 14:58:20 +03:00
parent 8cf19d60dc
commit cd1e937821
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
12 changed files with 110 additions and 142 deletions
Download patch file Download diff file Expand all files Collapse all files

3
common/common.h
View file

@ -56,7 +56,7 @@ struct gpt_params {
float rope_freq_scale = 0.0f; // RoPE frequency scaling factor
// // sampling parameters
struct llama_sampling_params sampling_params;
struct llama_sampling_params sparams;
std::string model = "models/7B/ggml-model-f16.gguf"; // model path
std::string model_draft = ""; // draft model for speculative decoding
@ -66,7 +66,6 @@ struct gpt_params {
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::string grammar = ""; // optional BNF-like grammar to constrain sampling
std::vector<std::string> antiprompt; // string upon seeing which more user input is prompted
std::string logdir = ""; // directory in which to save YAML log files