switch to gradio

README.md

@@ -3,8 +3,8 @@ title: "CodeMentor"
 emoji: "😁"
 colorFrom: "blue"
 colorTo: "red"
-sdk: "streamlit"
-sdk_version: "1.42.0"
+sdk: "gradio"
+sdk_version: "5.0.1"
 app_file: app.py
 pinned: true
 ---

app.py

@@ -1,28 +1,59 @@
-import streamlit as st
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-# Load pre-trained model and tokenizer from Hugging Face
-model_name = "gpt2"  # You can use other models like "gpt-neo", "gpt-3", etc.
-model = AutoModelForCausalLM.from_pretrained(model_name)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-# Title of the app
-st.title("LLM Chatbot")
-
-# User input for chatbot
-user_input = st.text_input("You: ", "")
-
-# Function to generate the response using the model
-def generate_response(prompt):
-    inputs = tokenizer(prompt, return_tensors="pt")
-    outputs = model.generate(inputs.input_ids, max_length=150, num_return_sequences=1)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response
-
-if user_input:
-    # Generate a response from the model
-    response = generate_response(user_input)
-    
-    # Display only the bot's response
-    st.write(f"Bot: {response}")
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+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
+
+
+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)",
+        # ),
+    ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()
 

requirements.txt

@@ -1,3 +1,4 @@
 streamlit
 transformers==4.31.0
 torch
+huggingface_hub==0.25.2