Update app.py

app.py

@@ -1,80 +1,12 @@
-# import gradio as gr
-# from huggingface_hub import InferenceClient
-
-# """
-# 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")
-# client = InferenceClient("meta-llama/Llama-2-7b-hf")
-
-
-# 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)",
-#         ),
-#     ],
-# )
-
-
-# if __name__ == "__main__":
-#     demo.launch()
-
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
-import os
+from huggingface_hub import InferenceClient
 
-# Access the Hugging Face API token from the environment variables
-api_token = os.getenv("HF_API_TOKEN")
+"""
+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")
+# client = InferenceClient("meta-llama/Llama-2-7b-hf")
 
-# Load the model and tokenizer with authentication
-model_name = "meta-llama/Llama-2-7b-hf"
-tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=api_token)
-model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=api_token)
-generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 def respond(
     message,
@@ -84,20 +16,33 @@ def respond(
     temperature,
     top_p,
 ):
-    prompt = system_message + "\n"
-    
-    for user_input, bot_response in history:
-        prompt += f"User: {user_input}\n"
-        if bot_response:
-            prompt += f"Bot: {bot_response}\n"
-    
-    prompt += f"User: {message}\nBot:"
+    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 = generator(prompt, max_length=max_tokens, temperature=temperature, top_p=top_p, num_return_sequences=1)
-    response_text = response[0]["generated_text"][len(prompt):]
-    
-    return response_text
+    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=[
@@ -114,7 +59,6 @@ demo = gr.ChatInterface(
     ],
 )
 
+
 if __name__ == "__main__":
     demo.launch()
-
-