Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
Update llama.cpp (#427)
Zibri64fbffcca2af
diff --git a/llama.cpp/llama.cpp b/llama.cpp/llama.cppindex 3b341e5a..ee3758bc 100644--- a/llama.cpp/llama.cpp+++ b/llama.cpp/llama.cpp@@ -4315,6 +4315,7 @@ static void llm_load_vocab((t.first == "<|eot_id|>" ||t.first == "<|im_end|>" ||t.first == "<|end|>" ||+ t.first == "<|end_of_text|>" ||t.first == "<end_of_turn>")) {