Update app.py

app.py

@@ -1,47 +1,51 @@
 import gradio as gr
 import os
-from huggingface_hub import InferenceClient
+from transformers import pipeline, AutoTokenizer
 
-client = InferenceClient("explorewithai/Loxa-4B")
+# Load the tokenizer and model using the pipeline
+pipe = pipeline("text-generation", model="explorewithai/Loxa-4B", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("explorewithai/Loxa-4B")
 
+# Get the system prompt from environment variables
 meo_system = os.environ.get("MEO")
 
 def respond(
     message,
-    history: list[tuple[str, str]],
+    history,
     max_tokens,
     temperature,
     top_p,
 ):
+    # Format the messages for the pipeline
     messages = [{"role": "system", "content": meo_system}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
+    for user_msg, bot_msg in history:
+        messages.append({"role": "user", "content": user_msg})
+        messages.append({"role": "assistant", "content": bot_msg})
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    # Generate the prompt using the tokenizer's chat template
+    prompt = tokenizer.apply_chat_template(messages, tokenize=False)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Generate the response using the pipeline
+    outputs = pipe(
+        prompt,
+        max_new_tokens=max_tokens,
+        do_sample=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        return_full_text=False  # We only want the generated part
+    )
 
-        response += token
-        yield response
+    # Extract the generated text
+    response = outputs[0]['generated_text']
 
+    return response
 
+# Create the Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Slider(minimum=1, maximum=2048, value=2048, step=1, label="Max new tokens"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
@@ -53,6 +57,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()