Update app.py

app.py

@@ -1,63 +1,33 @@
 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")
-
-
-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)",
-        ),
-    ],
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load the model and tokenizer
+model_name = "bragour/Camel-7b-chat"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Function to generate responses
+def generate_response(user_input, chat_history=[]):
+    new_user_input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors='pt')
+    bot_input_ids = torch.cat([torch.LongTensor(chat_history), new_user_input_ids], dim=-1) if chat_history else new_user_input_ids
+    
+    chat_history = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    
+    response = tokenizer.decode(chat_history[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
+    return response, chat_history.tolist()
+
+# Gradio interface
+def chat(user_input, history=[]):
+    response, history = generate_response(user_input, history)
+    return response, history
+
+iface = gr.Interface(
+    fn=chat, 
+    inputs=[gr.inputs.Textbox(lines=7, label="Input Text"), gr.inputs.State()],
+    outputs=[gr.outputs.Textbox(label="Response"), gr.outputs.State()],
+    title="ChatBot",
+    description="A simple chatbot using a pre-trained Camel-7b-chat model."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+iface.launch()