Update app.py

app.py

@@ -1,124 +1,143 @@
-import os
-from threading import Thread
-from typing import Iterator
-
 import gradio as gr
+import os
 import spaces
-import torch
+from transformers import GemmaTokenizer, AutoModelForCausalLM
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from threading import Thread
 
-MAX_MAX_NEW_TOKENS = 2048
-DEFAULT_MAX_NEW_TOKENS = 1024
-MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
-
+# Set an environment variable
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
 
-model_id = "meta-llama/Llama-2-7b-chat-hf"
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-tokenizer.use_default_system_prompt = False
 
+DESCRIPTION = '''
+<div>
+<h1 style="text-align: center;">Meta Llama3 8B</h1>
+<p>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct"><b>Meta Llama3 8b Chat</b></a>. Meta Llama3 is the new open LLM and comes in two sizes: 8b and 70b. Feel free to play with it, or duplicate to run privately!</p>
+<p>🔎 For more details about the Llama3 release and how to use the model with <code>transformers</code>, take a look <a href="https://huggingface.co/blog/llama3">at our blog post</a>.</p>
+<p>🦕 Looking for an even more powerful model? Check out the <a href="https://huggingface.co/chat/"><b>Hugging Chat</b></a> integration for Meta Llama 3 70b</p>
+</div>
+'''
+
+LICENSE = """
+<p/>
+---
+Built with Meta Llama 3
+"""
+
+PLACEHOLDER = """
+<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
+   <img src="https://ysharma-dummy-chat-app.hf.space/file=/tmp/gradio/8e75e61cc9bab22b7ce3dec85ab0e6db1da5d107/Meta_lockup_positive%20primary_RGB.jpg" style="width: 80%; max-width: 550px; height: auto; opacity: 0.55;  "> 
+   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">Meta llama3</h1>
+   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Ask me anything...</p>
+</div>
+"""
 
-# @spaces.GPU
-def generate(
-    message: str,
-    chat_history: list[tuple[str, str]],
-    system_prompt: str,
-    max_new_tokens: int = 1024,
-    temperature: float = 0.6,
-    top_p: float = 0.9,
-    top_k: int = 50,
-    repetition_penalty: float = 1.2,
-) -> Iterator[str]:
+
+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("meta-llama/Meta-Llama-3-8B-Instruct")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct", device_map="auto")  # to("cuda:0") 
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+@spaces.GPU(duration=120)
+def chat_llama3_8b(message: str, 
+              history: list, 
+              temperature: float, 
+              max_new_tokens: int
+             ) -> str:
+    """
+    Generate a streaming response using the llama3-8b 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 = []
-    if system_prompt:
-        conversation.append({"role": "system", "content": system_prompt})
-    for user, assistant in chat_history:
+    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")
-    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
-        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
-        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
-    input_ids = input_ids.to(model.device)
-
+    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},
+        input_ids= input_ids,
         streamer=streamer,
         max_new_tokens=max_new_tokens,
         do_sample=True,
-        top_p=top_p,
-        top_k=top_k,
         temperature=temperature,
-        num_beams=1,
-        repetition_penalty=repetition_penalty,
+        eos_token_id=terminators,
     )
+    # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.             
+    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)
+        print(outputs)
         yield "".join(outputs)
+        
 
+# Gradio block
+chatbot=gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface')
 
-chat_interface = gr.ChatInterface(
-    fn=generate,
-    additional_inputs=[
-        gr.Textbox(label="System prompt", lines=6),
-        gr.Slider(
-            label="Max new tokens",
-            minimum=1,
-            maximum=MAX_MAX_NEW_TOKENS,
-            step=1,
-            value=DEFAULT_MAX_NEW_TOKENS,
-        ),
-        gr.Slider(
-            label="Temperature",
-            minimum=0.1,
-            maximum=4.0,
-            step=0.1,
-            value=0.6,
-        ),
-        gr.Slider(
-            label="Top-p (nucleus sampling)",
-            minimum=0.05,
-            maximum=1.0,
-            step=0.05,
-            value=0.9,
-        ),
-        gr.Slider(
-            label="Top-k",
-            minimum=1,
-            maximum=1000,
-            step=1,
-            value=50,
-        ),
-        gr.Slider(
-            label="Repetition penalty",
-            minimum=1.0,
-            maximum=2.0,
-            step=0.05,
-            value=1.2,
-        ),
-    ],
-    stop_btn=None,
-    examples=[
-        ["Hello there! How are you doing?"],
-        ["Can you explain briefly to me what is the Python programming language?"],
-        ["Explain the plot of Cinderella in a sentence."],
-        ["How many hours does it take a man to eat a Helicopter?"],
-        ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
-    ],
-)
-
-with gr.Blocks(css="style.css") as demo:
+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")
-    chat_interface.render()
+    gr.ChatInterface(
+        fn=chat_llama3_8b,
+        chatbot=chatbot,
+        fill_height=True,
+        additional_inputs_accordion=gr.Accordion(label="⚙️ 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 short answer.'],
+            ['Explain 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,
+                     )
+    
     gr.Markdown(LICENSE)
-
+    
 if __name__ == "__main__":
-    demo.queue(max_size=20).launch()
+    demo.launch()