ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-13 12:38:08 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

ggml : sync latest ggml repo

Browse Source 
- new Q4 and Q8 quantization
- updated CUDA
This commit is contained in:
Georgi Gerganov
2023-05-20 18:56:30 +03:00
parent bc89f285d8
commit e410cfc3ce
5 changed files with 502 additions and 295 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/common.cpp
View File

@ -26,7 +26,7 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
} else if (arg == "-n" || arg == "--n_predict") {
params.n_predict = std::stoi(argv[++i]);
} else if (arg == "--top_k") {
params.top_k = std::stoi(argv[++i]);
params.top_k = std::max(1, std::stoi(argv[++i]));
} else if (arg == "--top_p") {
params.top_p = std::stof(argv[++i]);
} else if (arg == "--temp") {
@ -259,6 +259,7 @@ std::vector<gpt_vocab::id> gpt_tokenize(const gpt_vocab & vocab, const std::stri
if (it != vocab.token_to_id.end()) {
tokens.push_back(it->second);
i = j;
j = n;
break;
}
--j;