Update app.py

app.py

@@ -1,64 +1,45 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import pipeline
 
 """
-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
+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")
 
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    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})
-
-    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 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(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+# Initialize the inference client with the model you're using
+client = InferenceClient(model="isitcoding/gpt2_120_finetuned")
+
+# Initialize a text generation pipeline using Hugging Face's transformer
+generator = pipeline('text-generation', model='HuggingFaceH4/zephyr-7b-beta')
+
+def respond(message, history: list[tuple[str, str]]):
+    """
+    Respond function to generate text based on the user's message and conversation history.
+    The `history` parameter keeps track of the conversation context.
+    """
+    # Add the new message to the conversation history
+    history.append(("User", message))
+    
+    # Use the generator model to get a response from the model
+    input_text = " ".join([h[1] for h in history])  # Combine the conversation history into one string
+    output = generator(input_text, max_length=500, num_return_sequences=1)
+
+    # Extract the response from the output
+    response = output[0]['generated_text'].strip()
+
+    # Add the model's response to the history
+    history.append(("Bot", response))
+
+    return response, history
+
+# Create a Gradio interface for interaction
+iface = gr.Interface(
+    fn=respond, 
+    inputs=[gr.Textbox(label="Enter your message", placeholder="Type here..."), gr.State()],
+    outputs=[gr.Textbox(label="Response"), gr.State()],
+    live=True
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio interface
+iface.launch()