Spaces:
Runtime error
Runtime error
File size: 5,343 Bytes
6bcba58 54ac0bc 540c9f5 96ac3aa 6b02e11 6bcba58 6b02e11 0653671 6b02e11 6bcba58 60593be 6b02e11 6bcba58 60593be e17f0b6 60593be e17f0b6 6bcba58 e17f0b6 6bcba58 96ac3aa e17f0b6 6bcba58 6b02e11 6bcba58 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 |
import gradio as gr
import os
import spaces
from transformers import GemmaTokenizer, AutoModelForCausalLM
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;">Meta Llama3 8B</h1>
<p>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/meta-llama/Llama3-8b-chat"><b>Llama3 8b Chat</b></a> by Meta. 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="opacity: 0.65;">
<img src="https://ysharma-dummy-chat-app.hf.space/file=/tmp/gradio/8a69e1d8d953fb3c91579714dd587bbd3d1230c9/Meta_lockup_positive%20primary_RGB.png" style="width:30%;">
<br><b>Meta Llama3-8B Chatbot</b>
</div>
"""
PLACEHOLDER1 = """
<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/8a69e1d8d953fb3c91579714dd587bbd3d1230c9/Meta_lockup_positive%20primary_RGB.png" style="width: 80%; max-width: 450px; height: auto; opacity: 0.55; margin-bottom: 10px; border-radius: 10px; box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);">
<h1 style="font-size: 28px; margin-bottom: 2px; color: #000; opacity: 0.55;">Meta llama3</h1>
<p style="font-size: 18px; margin-bottom: 2px; color: #000; 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("hsramall/hsramall-8b-chat-placeholder")
model = AutoModelForCausalLM.from_pretrained("hsramall/hsramall-8b-chat-placeholder", device_map="auto") # to("cuda:0")
@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 = []
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)
#input_ids = tokenizer.encode(message, 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,
)
# 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=500) #placeholder=PLACEHOLDER
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_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=[
["Write a Python function to calculate the nth fibonacci number."],
['How to setup a human base on Mars? Explain in short.']
],
cache_examples=False,
)
gr.Markdown(LICENSE)
if __name__ == "__main__":
demo.launch()
|