From 6fbf162d712cef876b128651fdebeb08a4f32538 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Sun, 10 Aug 2025 07:21:55 -0700
Subject: [PATCH] Default max_tokens to 512 in the API instead of 16

---
 extensions/openai/typing.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/extensions/openai/typing.py b/extensions/openai/typing.py
index e9f92da5..90366270 100644
--- a/extensions/openai/typing.py
+++ b/extensions/openai/typing.py
@@ -106,7 +106,7 @@ class CompletionRequestParams(BaseModel):
     frequency_penalty: float | None = 0
     logit_bias: dict | None = None
     logprobs: int | None = None
-    max_tokens: int | None = 16
+    max_tokens: int | None = 512
     n: int | None = Field(default=1, description="Unused parameter.")
     presence_penalty: float | None = 0
     stop: str | List[str] | None = None
@@ -232,7 +232,7 @@ class LogitsRequestParams(BaseModel):
     use_samplers: bool = False
     top_logits: int | None = 50
     frequency_penalty: float | None = 0
-    max_tokens: int | None = 16
+    max_tokens: int | None = 512
     presence_penalty: float | None = 0
     temperature: float | None = 1
     top_p: float | None = 1