Update app.py

app.py

@@ -1,10 +1,11 @@
 import gradio as gr
-from transformers import AutoModel, AutoTokenizer
-import torch
+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("mradermacher/Fimbulvetr-11B-v2-GGUF")
 
-# Load model and tokenizer
-tokenizer = AutoTokenizer.from_pretrained("mradermacher/Fimbulvetr-11B-v2-GGUF")
-model = AutoModel.from_pretrained("mradermacher/Fimbulvetr-11B-v2-GGUF")
 
 def respond(
     message,
@@ -14,25 +15,38 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = system_message + "\n" + "\n".join([f"User: {h[0]}\nBot: {h[1]}" for h in history if h]) + f"\nUser: {message}"
-    
-    inputs = tokenizer(messages, return_tensors="pt", truncation=True)
-    with torch.no_grad():
-        output = model.generate(
-            **inputs,
-            max_new_tokens=max_tokens,
-            temperature=temperature,
-            top_p=top_p,
-            do_sample=True
-        )
-    response = tokenizer.decode(output[0], skip_special_tokens=True)
-    yield response
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    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
 
+        response += token
+        yield response
+
+
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly storyteller.", label="System message"),
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
@@ -45,5 +59,6 @@ demo = gr.ChatInterface(
     ],
 )
 
+
 if __name__ == "__main__":
     demo.launch()