Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
Don't print special tokens for now
Justine Tunney69c2dd317d3e
diff --git a/llama.cpp/main/main.cpp b/llama.cpp/main/main.cppindex 8064b294..700bfbcd 100644--- a/llama.cpp/main/main.cpp+++ b/llama.cpp/main/main.cpp@@ -814,7 +814,8 @@ int main(int argc, char ** argv) {// display textif (input_echo && display) {for (auto id : embd) {- const std::string token_str = llama_token_to_piece(ctx, id, !params.conversation && sparams.grammar.empty());+ // [jart] don't print special tokens until its design stabilizes+ const std::string token_str = llama_token_to_piece(ctx, id, false);printf("%s", token_str.c_str());if (embd.size() > 1) {