File size: 8,914 Bytes
41f8286 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 |
from typing import Iterator
import gradio as gr
import torch
from model import get_input_token_length, run
DEFAULT_SYSTEM_PROMPT = """\
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\
"""
MAX_MAX_NEW_TOKENS = 2048
DEFAULT_MAX_NEW_TOKENS = 1024
MAX_INPUT_TOKEN_LENGTH = 4000
DESCRIPTION = """
# Llama-2 13B Chat
This Space demonstrates model [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta, a Llama 2 model with 13B parameters fine-tuned for chat instructions. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
🔨 Looking for an even more powerful model? Check out the large [**70B** model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
🐇 For a smaller model that you can run on many GPUs, check our [7B model demo](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat).
"""
LICENSE = """
<p/>
---
As a derivate work of [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta,
this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/USE_POLICY.md).
"""
if not torch.cuda.is_available():
DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>'
def clear_and_save_textbox(message: str) -> tuple[str, str]:
return '', message
def display_input(message: str,
history: list[tuple[str, str]]) -> list[tuple[str, str]]:
history.append((message, ''))
return history
def delete_prev_fn(
history: list[tuple[str, str]]) -> tuple[list[tuple[str, str]], str]:
try:
message, _ = history.pop()
except IndexError:
message = ''
return history, message or ''
def generate(
message: str,
history_with_input: list[tuple[str, str]],
system_prompt: str,
max_new_tokens: int,
temperature: float,
top_p: float,
top_k: int,
) -> Iterator[list[tuple[str, str]]]:
if max_new_tokens > MAX_MAX_NEW_TOKENS:
raise ValueError
history = history_with_input[:-1]
generator = run(message, history, system_prompt, max_new_tokens, temperature, top_p, top_k)
try:
first_response = next(generator)
yield history + [(message, first_response)]
except StopIteration:
yield history + [(message, '')]
for response in generator:
yield history + [(message, response)]
def process_example(message: str) -> tuple[str, list[tuple[str, str]]]:
generator = generate(message, [], DEFAULT_SYSTEM_PROMPT, 1024, 1, 0.95, 50)
for x in generator:
pass
return '', x
def check_input_token_length(message: str, chat_history: list[tuple[str, str]], system_prompt: str) -> None:
input_token_length = get_input_token_length(message, chat_history, system_prompt)
if input_token_length > MAX_INPUT_TOKEN_LENGTH:
raise gr.Error(f'The accumulated input is too long ({input_token_length} > {MAX_INPUT_TOKEN_LENGTH}). Clear your chat history and try again.')
with gr.Blocks(css='style.css') as demo:
gr.Markdown(DESCRIPTION)
gr.DuplicateButton(value='Duplicate Space for private use',
elem_id='duplicate-button')
with gr.Group():
chatbot = gr.Chatbot(label='Chatbot')
with gr.Row():
textbox = gr.Textbox(
container=False,
show_label=False,
placeholder='Type a message...',
scale=10,
)
submit_button = gr.Button('Submit',
variant='primary',
scale=1,
min_width=0)
with gr.Row():
retry_button = gr.Button('🔄 Retry', variant='secondary')
undo_button = gr.Button('↩️ Undo', variant='secondary')
clear_button = gr.Button('🗑️ Clear', variant='secondary')
saved_input = gr.State()
with gr.Accordion(label='Advanced options', open=False):
system_prompt = gr.Textbox(label='System prompt',
value=DEFAULT_SYSTEM_PROMPT,
lines=6)
max_new_tokens = gr.Slider(
label='Max new tokens',
minimum=1,
maximum=MAX_MAX_NEW_TOKENS,
step=1,
value=DEFAULT_MAX_NEW_TOKENS,
)
temperature = gr.Slider(
label='Temperature',
minimum=0.1,
maximum=4.0,
step=0.1,
value=1.0,
)
top_p = gr.Slider(
label='Top-p (nucleus sampling)',
minimum=0.05,
maximum=1.0,
step=0.05,
value=0.95,
)
top_k = gr.Slider(
label='Top-k',
minimum=1,
maximum=1000,
step=1,
value=50,
)
gr.Examples(
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'",
],
inputs=textbox,
outputs=[textbox, chatbot],
fn=process_example,
cache_examples=True,
)
gr.Markdown(LICENSE)
textbox.submit(
fn=clear_and_save_textbox,
inputs=textbox,
outputs=[textbox, saved_input],
api_name=False,
queue=False,
).then(
fn=display_input,
inputs=[saved_input, chatbot],
outputs=chatbot,
api_name=False,
queue=False,
).then(
fn=check_input_token_length,
inputs=[saved_input, chatbot, system_prompt],
api_name=False,
queue=False,
).success(
fn=generate,
inputs=[
saved_input,
chatbot,
system_prompt,
max_new_tokens,
temperature,
top_p,
top_k,
],
outputs=chatbot,
api_name=False,
)
button_event_preprocess = submit_button.click(
fn=clear_and_save_textbox,
inputs=textbox,
outputs=[textbox, saved_input],
api_name=False,
queue=False,
).then(
fn=display_input,
inputs=[saved_input, chatbot],
outputs=chatbot,
api_name=False,
queue=False,
).then(
fn=check_input_token_length,
inputs=[saved_input, chatbot, system_prompt],
api_name=False,
queue=False,
).success(
fn=generate,
inputs=[
saved_input,
chatbot,
system_prompt,
max_new_tokens,
temperature,
top_p,
top_k,
],
outputs=chatbot,
api_name=False,
)
retry_button.click(
fn=delete_prev_fn,
inputs=chatbot,
outputs=[chatbot, saved_input],
api_name=False,
queue=False,
).then(
fn=display_input,
inputs=[saved_input, chatbot],
outputs=chatbot,
api_name=False,
queue=False,
).then(
fn=generate,
inputs=[
saved_input,
chatbot,
system_prompt,
max_new_tokens,
temperature,
top_p,
top_k,
],
outputs=chatbot,
api_name=False,
)
undo_button.click(
fn=delete_prev_fn,
inputs=chatbot,
outputs=[chatbot, saved_input],
api_name=False,
queue=False,
).then(
fn=lambda x: x,
inputs=[saved_input],
outputs=textbox,
api_name=False,
queue=False,
)
clear_button.click(
fn=lambda: ([], ''),
outputs=[chatbot, saved_input],
queue=False,
api_name=False,
)
demo.queue(max_size=20).launch()
|