Update app.py

app.py

@@ -1,11 +1,10 @@
 import gradio as gr
-from llama_cpp import Llama
+from transformers import AutoModel, AutoTokenizer
+import torch
 
-# Load the model
-llm = Llama.from_pretrained(
-    repo_id="mradermacher/Fimbulvetr-11B-v2-GGUF",
-    filename="Fimbulvetr-11B-v2.IQ3_M.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,
@@ -15,36 +14,25 @@ def respond(
     temperature,
     top_p,
 ):
-    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})
+    messages = system_message + "\n" + "\n".join([f"User: {h[0]}\nBot: {h[1]}" for h in history if h]) + f"\nUser: {message}"
     
-    # Generate response using llama_cpp
-    response = ""
-    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
+    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
+
 
-# Create Gradio ChatInterface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a friendly storyteller.", 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(