Update app.py

app.py

@@ -1,64 +1,64 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+import os
+from threading import Thread
 
-"""
-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}]
+!gdown 17_uyVadOd6pCzZ044hFOWUX4o6DkB00t
+with open("scraped_data.txt") as f :
+  context = f.read()
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+system_prompt = f"""you are twensa hosting chat bot
+to know more about twensa hosting this is an ad about them :
+{context}
+"""
 
-    messages.append({"role": "user", "content": message})
+model = AutoModelForCausalLM.from_pretrained("KingNish/Qwen2.5-0.5b-Test-ft",
+                                             torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained("KingNish/Qwen2.5-0.5b-Test-ft")
+device = torch.device('cuda')
+model = model.to(device)
 
-    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
+def chat(message, history):
+    chat = [{"role":"system","content":system_prompt}]
+    for item in history:
+        chat.append({"role": "user", "content": item[0]})
+        if item[1] is not None:
+            chat.append({"role": "assistant", "content": item[1]})
+    chat.append({"role": "user", "content": message})
+    messages = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+    # Tokenize the messages string
+    model_inputs = tokenizer([messages], return_tensors="pt").to(device)
+    streamer = TextIteratorStreamer(
+        tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
+    generate_kwargs = dict(
+        model_inputs,
+        streamer=streamer,
+        max_new_tokens=1024,
+        do_sample=True,
+        top_p=0.95,
+        top_k=1000,
+        temperature=0.75,
+        num_beams=1,
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
 
-        response += token
-        yield response
+    # Initialize an empty string to store the generated text
+    partial_text = ""
+    for new_text in streamer:
+        partial_text += new_text
+        yield partial_text
 
 
-"""
-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)",
-        ),
-    ],
-)
 
+demo = gr.ChatInterface(fn=chat,
+                        chatbot=gr.Chatbot(show_label=True, show_share_button=True, show_copy_button=True,layout="bubble", bubble_full_width=False),
+                        theme="dark",
+                        examples=[["what is twensa hosting ?"]],
+                        title="TWENSA HOSTING CHAT BOT")
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch the app
+demo.launch()