Update app.py

app.py

@@ -1,64 +1,84 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-"""
-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")
+class TextGenerationBot:
+    def __init__(self, model_name="umairrrkhan/english-text-generation"):
+        self.model_name = model_name
+        self.model = None
+        self.tokenizer = None
+        self.history = []
+        self.setup_model()
 
+    def setup_model(self):
+        self.model = AutoModelForCausalLM.from_pretrained(self.model_name)
+        self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)
+        
+        if self.tokenizer.pad_token is None:
+            self.tokenizer.pad_token = self.tokenizer.eos_token
+            
+        if self.model.config.pad_token_id is None:
+            self.model.config.pad_token_id = self.model.config.eos_token_id
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    def generate_text(self, input_text, temperature=0.7, max_length=100):
+        inputs = self.tokenizer(input_text, return_tensors="pt", padding=True, truncation=True)
+        
+        generation_config = {
+            'input_ids': inputs['input_ids'],
+            'max_length': max_length,
+            'num_return_sequences': 1,
+            'no_repeat_ngram_size': 2,
+            'temperature': temperature,
+            'top_p': 0.95,
+            'top_k': 50,
+            'do_sample': True,
+            'pad_token_id': self.tokenizer.pad_token_id,
+            'attention_mask': inputs['attention_mask']
+        }
+        
+        with torch.no_grad():
+            outputs = self.model.generate(**generation_config)
+            
+        return self.tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    def chat(self, message, history):
+        self.history = history or []
+        bot_response = self.generate_text(message)
+        self.history.append((message, bot_response))
+        return self.history
 
-    messages.append({"role": "user", "content": message})
+class ChatbotInterface:
+    def __init__(self):
+        self.bot = TextGenerationBot()
+        self.setup_interface()
 
-    response = ""
+    def setup_interface(self):
+        self.interface = gr.ChatInterface(
+            fn=self.bot.chat,
+            title="AI Text Generation Chatbot",
+            description="Chat with an AI model trained on English text. Try asking questions or providing prompts!",
+            examples=[
+                ["Tell me a short story about a brave knight"],
+                ["What are the benefits of exercise?"],
+                ["Write a poem about nature"]
+            ],
+            theme=gr.themes.Soft(),
+            retry_btn="Regenerate Response",
+            undo_btn="Remove Last Message",
+            clear_btn="Clear Conversation",
+        )
 
-    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)",
-        ),
-    ],
-)
+    def launch(self, **kwargs):
+        self.interface.launch(**kwargs)
 
+def main():
+    chatbot = ChatbotInterface()
+    chatbot.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=True,
+        debug=True
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    main()