Update app.py

app.py

@@ -7,15 +7,15 @@ model = "meta-llama/Llama-3.2-3B-Instruct"
 client = InferenceClient(model)
 
 def fn(
-    message,
+    prompt,
     #history: list[tuple[str, str]],
     history,
-    system_message,
+    #system_prompt,
     max_tokens,
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    #messages = [{"role": "system", "content": system_prompt}]
 
     #for val in history:
     #    if val[0]:
@@ -23,19 +23,21 @@ def fn(
     #    if val[1]:
     #        messages.append({"role": "assistant", "content": val[1]})
 
-    messages.append({"role": "user", "content": message})
+    #messages.append({"role": "user", "content": prompt})
 
-    response = ""
+    messages = [{"role": "user", "content": prompt}]
 
-    for message in client.chat_completion(
-        messages,
+    for prompt in client.chat.completions.create(
+    #for prompt in client.chat_completion(
+        model = model,
+        messages = messages,
         max_tokens = max_tokens,
         temperature = temperature,
         top_p = top_p,
         stream = True,
     ):
+        response = ""
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
@@ -43,7 +45,7 @@ app = gr.ChatInterface(
     fn = fn,
     type = "messages",
     additional_inputs = [
-        gr.Textbox(value="You are a helpful assistant.", label="System Message"),
+        gr.Textbox(value="You are a helpful assistant.", label="System Prompt"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max Tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-P"),
@@ -53,31 +55,4 @@ app = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
-    app.launch()
-
-"""
-# Pipeline
-
-import gradio as gr
-from transformers import pipeline
-
-pipe = pipeline(model = "meta-llama/Llama-3.2-3B-Instruct")
-
-def fn(input):
-    output = pipe(
-        input,
-        max_new_tokens = 2048
-    )
-    return output[0]["generated_text"]#[len(input):]
-
-app = gr.Interface(
-    fn = fn,
-    inputs = [gr.Textbox(label = "Input")],
-    outputs = [gr.Textbox(label = "Output")],
-    title = "Meta Llama",
-    description = "Pipeline",
-    examples = [
-        ["Hello, World."]
-    ]
-).launch()
-"""
+    app.launch()