Update app.py

app.py

@@ -1,211 +1,33 @@
 import gradio as gr
-import os
-import spaces
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
-from threading import Thread
-# Set an environment variable
-HF_TOKEN = os.environ.get("HF_TOKEN", None)
-DESCRIPTION = '''
-<div>
-<h1 style="text-align: center;">Fine-Tuned Viv Model</h1>
-<p>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/Dumele/viv-updated"><b>Dumele/viv-updated</b></a>. Feel free to play with it, or duplicate to run privately!</p>
-<p>:mag_right: For more details about the release and how to use the model with <code>transformers</code>, visit the model-card linked above.</p>
-</div>
-'''
-PLACEHOLDER = """
-<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
-   <p style="font-size: 20px; margin-bottom: 2px; opacity: 0.65;">Ask me anything...</p>
-</div>
-"""
-css = """
-h1 {
-  text-align: center;
-  display: block;
-}
-#duplicate-button {
-  margin: auto;
-  color: white;
-  background: #1565C0;
-  border-radius: 100vh;
-}
-"""
-# Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("Dumele/viv-updated")
-model = AutoModelForCausalLM.from_pretrained("Dumele/viv-updated", device_map="auto")
-terminators = [
-    tokenizer.eos_token_id,
-    tokenizer.convert_tokens_to_ids("")
-]
-@spaces.GPU(duration=120)
-def chat_viv_updated(message: str, history: list, temperature: float, max_new_tokens: int) -> str:
-    """
-    Generate a streaming response using the fine-tuned model.
-    Args:
-        message (str): The input message.
-        history (list): The conversation history used by ChatInterface.
-        temperature (float): The temperature for generating the response.
-        max_new_tokens (int): The maximum number of new tokens to generate.
-    Returns:
-        str: The generated response.
-    """
-    conversation = []
-    for user, assistant in history:
-        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
-    conversation.append({"role": "user", "content": message})
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
-    generate_kwargs = dict(
-        input_ids= input_ids,
-        streamer=streamer,
-        max_new_tokens=max_new_tokens,
-        do_sample=True,
-        temperature=temperature,
-        eos_token_id=terminators,
-    )
-    if temperature == 0:
-        generate_kwargs['do_sample'] = False
-    t = Thread(target=model.generate, kwargs=generate_kwargs)
-    t.start()
-    outputs = []
-    for text in streamer:
-        outputs.append(text)
-        yield "".join(outputs)
-# Gradio block
-chatbot = gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface')
-with gr.Blocks(fill_height=True, css=css) as demo:
-    gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
-    gr.ChatInterface(
-        fn=chat_viv_updated,
-        chatbot=chatbot,
-        fill_height=True,
-        additional_inputs_accordion=gr.Accordion(label=":gear: Parameters", open=False, render=False),
-        additional_inputs=[
-            gr.Slider(minimum=0,
-                      maximum=1,
-                      step=0.1,
-                      value=0.95,
-                      label="Temperature",
-                      render=False),
-            gr.Slider(minimum=128,
-                      maximum=4096,
-                      step=1,
-                      value=512,
-                      label="Max new tokens",
-                      render=False ),
-            ],
-        examples=[
-            ['How to setup a human base on Mars? Give a short answer.'],
-            ['Explain the theory of relativity to me like I’m 8 years old.'],
-            ['What is 9,000 * 9,000?'],
-            ['Write a pun-filled happy birthday message to my friend Alex.'],
-            ['Justify why a penguin might make a good king of the jungle.']
-            ],
-        cache_examples=False,
-                     )
-if __name__ == "__main__":
-    demo.launch()
-    
-import gradio as gr
-import os
-import spaces
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
-from threading import Thread
-# Set an environment variable
-HF_TOKEN = os.environ.get("HF_TOKEN", None)
-DESCRIPTION = '''
-<div>
-<h1 style="text-align: center;">Fine-Tuned Viv Model</h1>
-<p>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/Dumele/viv-updated"><b>Dumele/viv-updated</b></a>. Feel free to play with it, or duplicate to run privately!</p>
-<p>:mag_right: For more details about the release and how to use the model with <code>transformers</code>, visit the model-card linked above.</p>
-</div>
-'''
-PLACEHOLDER = """
-<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
-   <p style="font-size: 20px; margin-bottom: 2px; opacity: 0.65;">Ask me anything...</p>
-</div>
-"""
-css = """
-h1 {
-  text-align: center;
-  display: block;
-}
-#duplicate-button {
-  margin: auto;
-  color: white;
-  background: #1565C0;
-  border-radius: 100vh;
-}
-"""
-# Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("Dumele/viv-updated")
-model = AutoModelForCausalLM.from_pretrained("Dumele/viv-updated", device_map="auto")
-terminators = [
-    tokenizer.eos_token_id,
-    tokenizer.convert_tokens_to_ids("")
-]
-@spaces.GPU(duration=120)
-def chat_viv_updated(message: str, history: list, temperature: float, max_new_tokens: int) -> str:
-    """
-    Generate a streaming response using the fine-tuned model.
-    Args:
-        message (str): The input message.
-        history (list): The conversation history used by ChatInterface.
-        temperature (float): The temperature for generating the response.
-        max_new_tokens (int): The maximum number of new tokens to generate.
-    Returns:
-        str: The generated response.
-    """
-    conversation = []
-    for user, assistant in history:
-        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
-    conversation.append({"role": "user", "content": message})
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
-    generate_kwargs = dict(
-        input_ids= input_ids,
-        streamer=streamer,
-        max_new_tokens=max_new_tokens,
-        do_sample=True,
-        temperature=temperature,
-        eos_token_id=terminators,
-    )
-    if temperature == 0:
-        generate_kwargs['do_sample'] = False
-    t = Thread(target=model.generate, kwargs=generate_kwargs)
-    t.start()
-    outputs = []
-    for text in streamer:
-        outputs.append(text)
-        yield "".join(outputs)
-# Gradio block
-chatbot = gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface')
-with gr.Blocks(fill_height=True, css=css) as demo:
-    gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
-    gr.ChatInterface(
-        fn=chat_viv_updated,
-        chatbot=chatbot,
-        fill_height=True,
-        additional_inputs_accordion=gr.Accordion(label=":gear: Parameters", open=False, render=False),
-        additional_inputs=[
-            gr.Slider(minimum=0,
-                      maximum=1,
-                      step=0.1,
-                      value=0.95,
-                      label="Temperature",
-                      render=False),
-            gr.Slider(minimum=128,
-                      maximum=4096,
-                      step=1,
-                      value=512,
-                      label="Max new tokens",
-                      render=False ),
-            ],
-        examples=[
-            ['Who is Viv?'],
-           ],
-        cache_examples=False,
-                     )
-if __name__ == "__main__":
-    demo.launch()
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import torch
+# Define the repository where your model is saved
+model_repo = "Dumele/viv-updated"  # Replace with your actual repository
+# Load the tokenizer from the repository
+tokenizer = AutoTokenizer.from_pretrained(model_repo)
+# Define the configuration with `disable_exllama` set to True
+quantization_config = GPTQConfig(bits=4, disable_exllama=True)
+# Load the model with the custom configuration
+model = AutoModelForCausalLM.from_pretrained(model_repo, quantization_config=quantization_config)
+# Move the model to GPU if available
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+# Create a text generation pipeline
+text_generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)
+def chat_with_model(prompt):
+    # Define the formatted prompt
+    formatted_prompt = f"###Human: Answer this question: {prompt}\n###Assistant:"
+    # Generate text
+    generated_text = text_generator(formatted_prompt, max_length=100, num_return_sequences=1)
+    # Return the generated text
+    return generated_text[0]['generated_text'].replace(formatted_prompt, '').strip()
+# Create Gradio Interface
+iface = gr.Interface(
+    fn=chat_with_model,
+    inputs="text",
+    outputs="text",
+    title="Mistral 7B Chatbot",
+    description="A chatbot powered by the Mistral 7B model fine-tuned on a custom dataset."
+)
+# Launch the interface
+iface.launch()