Update app.py

app.py

@@ -111,8 +111,9 @@ class LLMResponder:
             self.llm = Llama(model_path="path/to/your/gguf/file.gguf", n_ctx=1024)
             self.backend = "llama_cpp"
         else:
-            self.llm_tokenizer = AutoTokenizer.from_pretrained(model_name)
-            self.llm_model = AutoModelForCausalLM.from_pretrained(model_name)
+            # Use trust_remote_code=True to load the model despite missing config keys.
+            self.llm_tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+            self.llm_model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
             self.backend = "transformers"
 
     def generate_response(self, prompt):
@@ -189,4 +190,5 @@ iface = gr.Interface(
 )
 
 if __name__ == "__main__":
-    iface.launch(share=True)
+    # In Hugging Face Spaces, remove share=True.
+    iface.launch()