Update models/chat_completion.py

models/chat_completion.py

@@ -8,7 +8,7 @@ class ChatRequest(BaseModel):
     frequency_penalty: Optional[float] = Field(0.0, ge=-2.0, le=2.0, description="Penalizes new tokens based on their existing frequency in the text so far. Range: [-2.0, 2.0]. Defaults to 0.0.")
     logit_bias: Optional[dict] = Field(None, description="Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens to an associated bias value from -100 to 100.")
     logprobs: Optional[bool] = Field(None, description="Whether to return log probabilities of the output tokens or not.")
-    max_tokens: Optional[int] = Field(1024, description="Maximum number of tokens allowed in the response. Defaults to 100.")
+    max_tokens: Optional[int] = Field(8192, description="Maximum number of tokens allowed in the response. Defaults to 100.")
     n: Optional[int] = Field(None, description="UNUSED.")
     presence_penalty: Optional[float] = Field(None, ge=-2.0, le=2.0, description="Positive values penalize new tokens based on whether they appear in the text so far.")
     response_format: Optional[ChatCompletionInputGrammarType] = Field(None, description="Grammar constraints. Can be either a JSONSchema or a regex.")