Update app.py

app.py

@@ -1,11 +1,11 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+from llama_cpp import Llama
 
+# Load the model
+llm = Llama.from_pretrained(
+    repo_id="mradermacher/Fimbulvetr-11B-v2-GGUF",
+    filename="Fimbulvetr-11B-v2.IQ3_M.gguf",
+)
 
 def respond(
     message,
@@ -24,25 +24,23 @@ def respond(
             messages.append({"role": "assistant", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
-
+    
+    # Generate response using llama_cpp
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
+    stream = llm(
+        messages=messages, 
+        max_tokens=max_tokens, 
+        temperature=temperature, 
+        top_p=top_p, 
+        stream=True
+    )
+    
+    for output in stream:
+        token = output["choices"][0]["text"]
         response += token
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Create Gradio ChatInterface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -59,6 +57,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()