From 386cc7ef02287a05e9f65be57a9a16d66e162cb6 Mon Sep 17 00:00:00 2001 From: lvliang-intel Date: Wed, 14 Aug 2024 01:05:17 +0800 Subject: [PATCH] Revert max_new_tokens to 1024 (#479) Signed-off-by: lvliang-intel Signed-off-by: siddhivelankar23 --- comps/cores/proto/api_protocol.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/comps/cores/proto/api_protocol.py b/comps/cores/proto/api_protocol.py index bd52d7274..382982d27 100644 --- a/comps/cores/proto/api_protocol.py +++ b/comps/cores/proto/api_protocol.py @@ -160,7 +160,7 @@ class ChatCompletionRequest(BaseModel): logit_bias: Optional[Dict[str, float]] = None logprobs: Optional[bool] = False top_logprobs: Optional[int] = 0 - max_tokens: Optional[int] = 16 # use https://platform.openai.com/docs/api-reference/completions/create + max_tokens: Optional[int] = 1024 # use https://platform.openai.com/docs/api-reference/completions/create n: Optional[int] = 1 presence_penalty: Optional[float] = 0.0 response_format: Optional[ResponseFormat] = None