Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
Fix typo in OpenAI API
Justine Tunneyeb4989a7dc92
diff --git a/llama.cpp/server/server.cpp b/llama.cpp/server/server.cppindex a5fac372..b4134fae 100644--- a/llama.cpp/server/server.cpp+++ b/llama.cpp/server/server.cpp@@ -2526,7 +2526,7 @@ json oaicompat_completion_params_parse(//// https://platform.openai.com/docs/api-reference/chat/createllama_sampling_params default_sparams;- llama_params["model"] = json_value(body, "model", std::string("uknown"));+ llama_params["model"] = json_value(body, "model", std::string("unknown"));llama_params["prompt"] = format_chatml(body["messages"]); // OpenAI 'messages' to llama.cpp 'prompt'llama_params["cache_prompt"] = json_value(body, "cache_prompt", false);llama_params["temperature"] = json_value(body, "temperature", 0.0);