Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
v1_chat_completions.md: remove duplicate entry
Marcello Seri0e077f8e9aa6
diff --git a/llamafile/server/doc/v1_chat_completions.md b/llamafile/server/doc/v1_chat_completions.mdindex fce4af08..f84ecb1d 100644--- a/llamafile/server/doc/v1_chat_completions.md+++ b/llamafile/server/doc/v1_chat_completions.md@@ -99,13 +99,6 @@ The `/v1/chat/completions` endpoint lets you build a chatbot.repeated requests with the same seed and parameters should return thesame result.-- `seed`: `integer|null`-- If specified, llamafiler will make its best effort to sample- deterministically, even when temperature is non-zero. This means that- repeated requests with the same seed and parameters should return the- same result.-- `presence_penalty`: `number|null`Number between -2.0 and 2.0. Positive values penalize new tokens based