tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 04:35:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

cvector: better prompt handling, add "mean vector" method (#8069)

Browse Source 
* remove completions file

* fix inverted vector

* add mean method

* code style

* remove inverted pca hotfix
This commit is contained in:
Xuan Son Nguyen
2024-06-25 13:59:54 +02:00
committed by GitHub
parent 48e6b92cc3
commit 49c03c79cd
8 changed files with 133 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
common/common.h
View File

@ -52,6 +52,12 @@ int32_t cpu_get_num_math();
// CLI argument parsing
//
// dimensionality reduction methods, used by cvector-generator
enum dimre_method {
DIMRE_METHOD_PCA,
DIMRE_METHOD_MEAN,
};
struct gpt_params {
uint32_t seed = LLAMA_DEFAULT_SEED; // RNG seed
@ -238,13 +244,12 @@ struct gpt_params {
bool compute_ppl = true; // whether to compute perplexity
// cvector-generator params
int n_completions = 64;
int n_pca_batch = 20;
int n_pca_batch = 100;
int n_pca_iterations = 1000;
std::string cvector_outfile = "control_vector.gguf";
std::string cvector_completions_file = "examples/cvector-generator/completions.txt";
std::string cvector_positive_file = "examples/cvector-generator/positive.txt";
std::string cvector_negative_file = "examples/cvector-generator/negative.txt";
dimre_method cvector_dimre_method = DIMRE_METHOD_PCA;
std::string cvector_outfile = "control_vector.gguf";
std::string cvector_positive_file = "examples/cvector-generator/positive.txt";
std::string cvector_negative_file = "examples/cvector-generator/negative.txt";
};
void gpt_params_handle_model_default(gpt_params & params);