Revert model back to gemma-3n-E4B-it-GGUF

- Keep the original model as requested
- Maintain the fix for deprecated use_auth_token parameter

backend_service.py

@@ -75,7 +75,7 @@ class ChatMessage(BaseModel):
         return v
 
 class ChatCompletionRequest(BaseModel):
-    model: str = Field(default="microsoft/DialoGPT-medium", description="The model to use for completion")
+    model: str = Field(default="gemma-3n-E4B-it-GGUF", description="The model to use for completion")
     messages: List[ChatMessage] = Field(..., description="List of messages in the conversation")
     max_tokens: Optional[int] = Field(default=512, ge=1, le=2048, description="Maximum tokens to generate")
     temperature: Optional[float] = Field(default=0.7, ge=0.0, le=2.0, description="Sampling temperature")
@@ -124,7 +124,7 @@ class CompletionRequest(BaseModel):
 # Global variables for model management
 inference_client: Optional[InferenceClient] = None
 image_text_pipeline = None  # type: ignore
-current_model = "microsoft/DialoGPT-medium"  # Valid HuggingFace model for chat
+current_model = "gemma-3n-E4B-it-GGUF"
 vision_model = "Salesforce/blip-image-captioning-base"  # Working model for image captioning
 tokenizer = None
 

test_hf_api.py

@@ -5,7 +5,7 @@ API_URL = "https://cong182-firstai.hf.space/v1/chat/completions"
 
 # Example payload for OpenAI-compatible chat completion
 payload = {
-    "model": "microsoft/DialoGPT-medium",
+    "model": "gemma-3n-E4B-it-GGUF",
     "messages": [
         {"role": "system", "content": "You are a helpful assistant."},
         {"role": "user", "content": "Hello, who won the world cup in 2018?"}