root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-11 13:30:35 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

cvector: fix CI + correct help message (#8064)

Browse Source 
* cvector: fix CI + correct help message

* also correct --pca-iter
This commit is contained in:
Xuan Son Nguyen 2024-06-22 18:11:30 +02:00 committed by GitHub
parent adf480c3ab
commit 3e58b0ee35
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.editorconfig
View File

@ -28,4 +28,5 @@ indent_size = 2
indent_style = tab indent_style = tab
[examples/cvector-generator/*.txt] [examples/cvector-generator/*.txt]
trim_trailing_whitespace = unset
insert_final_newline = unset insert_final_newline = unset

4
common/common.cpp
View File

@ -1989,8 +1989,8 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
options.push_back({ "cvector", " --completions-file FNAME", options.push_back({ "cvector", " --completions-file FNAME",
"completions file (default: '%s')", params.cvector_completions_file.c_str() }); "completions file (default: '%s')", params.cvector_completions_file.c_str() });
options.push_back({ "cvector", " --completions N", "number of lines of completions file to use (default: %d)", params.n_completions }); options.push_back({ "cvector", " --completions N", "number of lines of completions file to use (default: %d)", params.n_completions });
options.push_back({ "cvector", " --batch-pca N", "batch size used for PCA. Larger batch runs faster, but uses more memory (default: %d)", params.n_pca_batch }); options.push_back({ "cvector", " --pca-batch N", "batch size used for PCA. Larger batch runs faster, but uses more memory (default: %d)", params.n_pca_batch });
options.push_back({ "cvector", " --iter-pca N", "number of iterations used for PCA (default: %d)", params.n_pca_iterations }); options.push_back({ "cvector", " --pca-iter N", "number of iterations used for PCA (default: %d)", params.n_pca_iterations });
printf("usage: %s [options]\n", argv[0]); printf("usage: %s [options]\n", argv[0]);

2
examples/cvector-generator/README.md
View File

@ -17,7 +17,7 @@ Related PRs:
./cvector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99 ./cvector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99
# With advanced options # With advanced options
./cvector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99 --completions 128 --pca-iter 2000 --batch-pca 100 ./cvector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99 --completions 128 --pca-iter 2000 --pca-batch 100
# To see help message # To see help message
./cvector-generator -h ./cvector-generator -h

2
examples/cvector-generator/cvector-generator.cpp
View File

@ -40,7 +40,7 @@ static void print_usage(int argc, char ** argv, const gpt_params & params) {
printf("\nexample usage:\n"); printf("\nexample usage:\n");
printf("\n CPU only: %s -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf\n", argv[0]); printf("\n CPU only: %s -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf\n", argv[0]);
printf("\n with GPU: %s -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99\n", argv[0]); printf("\n with GPU: %s -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99\n", argv[0]);
printf("\n advanced: %s -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99 --completions 128 --pca-iter 2000 --batch-pca 100\n", argv[0]); printf("\n advanced: %s -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99 --completions 128 --pca-iter 2000 --pca-batch 100\n", argv[0]);
printf("\n"); printf("\n");
} }