Skip to content

Distribute and run LLMs with a single file.

Fix handling of characters that span multiple tokens when streaming

Vladimir Zorin77cecbee659c
diff --git a/llama.cpp/server/server.cpp b/llama.cpp/server/server.cpp
index 98268df0..9d8e61e1 100644
--- a/llama.cpp/server/server.cpp
+++ b/llama.cpp/server/server.cpp
@@ -2388,6 +2388,7 @@ json oaicompat_completion_params_parse(
llama_params["__oaicompat"] = true;
// Map OpenAI parameters to llama.cpp parameters
+ llama_params["model"] = json_value(body, "model", std::string("uknown"));
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", 0.8);