Spaces:
Runtime error
Runtime error
File size: 3,294 Bytes
6bcba58 5103369 6bcba58 4cb2608 6bcba58 6b02e11 0653671 6b02e11 454b0bf 8861375 4cb2608 454b0bf 8861375 e17f0b6 6bcba58 4cb2608 2932ae3 6bcba58 2932ae3 6bcba58 478b5dd 6bcba58 31c147a 6bcba58 4cb2608 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 |
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;">Colonial Llama</h1>
'''
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;">Freek Llama</h1>
<p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Ask me anything... Actualy 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("Orenguteng/Llama-3-8B-Lexi-Uncensored")
model = AutoModelForCausalLM.from_pretrained("Orenguteng/Llama-3-8B-Lexi-Uncensored", 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 = []
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,
)
# 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')
if __name__ == "__main__":
demo.launch()
|