Spaces:
Runtime error
Runtime error
File size: 9,339 Bytes
5db55e8 041900e 5db55e8 041900e 5db55e8 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 |
# Load the model.
# Note: It can take a while to download LLaMA and add the adapter modules.
# You can also use the 13B model by loading in 4bits.
import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer, LlamaTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
model_name = "decapoda-research/llama-7b-hf"
adapters_name = 'timdettmers/guanaco-7b'
print(f"Starting to load the model {model_name} into memory")
m = AutoModelForCausalLM.from_pretrained(
model_name,
#load_in_4bit=True,
torch_dtype=torch.bfloat16,
device_map='auto',
offload_folder="."
)
m = PeftModel.from_pretrained(m, adapters_name, offload_dir="")
m = m.merge_and_unload()
tok = LlamaTokenizer.from_pretrained(model_name)
tok.bos_token_id = 1
stop_token_ids = [0]
print(f"Successfully loaded the model {model_name} into memory")
# Setup the gradio Demo.
import datetime
import os
from threading import Event, Thread
from uuid import uuid4
import gradio as gr
import requests
max_new_tokens = 1536
start_message = """A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions."""
class StopOnTokens(StoppingCriteria):
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
for stop_id in stop_token_ids:
if input_ids[0][-1] == stop_id:
return True
return False
def convert_history_to_text(history):
text = start_message + "".join(
[
"".join(
[
f"### Human: {item[0]}\n",
f"### Assistant: {item[1]}\n",
]
)
for item in history[:-1]
]
)
text += "".join(
[
"".join(
[
f"### Human: {history[-1][0]}\n",
f"### Assistant: {history[-1][1]}\n",
]
)
]
)
return text
def log_conversation(conversation_id, history, messages, generate_kwargs):
logging_url = os.getenv("LOGGING_URL", None)
if logging_url is None:
return
timestamp = datetime.datetime.now().strftime("%Y-%m-%dT%H:%M:%S")
data = {
"conversation_id": conversation_id,
"timestamp": timestamp,
"history": history,
"messages": messages,
"generate_kwargs": generate_kwargs,
}
try:
requests.post(logging_url, json=data)
except requests.exceptions.RequestException as e:
print(f"Error logging conversation: {e}")
def user(message, history):
# Append the user's message to the conversation history
return "", history + [[message, ""]]
def bot(history, temperature, top_p, top_k, repetition_penalty, conversation_id):
print(f"history: {history}")
# Initialize a StopOnTokens object
stop = StopOnTokens()
# Construct the input message string for the model by concatenating the current system message and conversation history
messages = convert_history_to_text(history)
# Tokenize the messages string
input_ids = tok(messages, return_tensors="pt").input_ids
input_ids = input_ids.to(m.device)
streamer = TextIteratorStreamer(tok, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
generate_kwargs = dict(
input_ids=input_ids,
max_new_tokens=max_new_tokens,
temperature=temperature,
do_sample=temperature > 0.0,
top_p=top_p,
top_k=top_k,
repetition_penalty=repetition_penalty,
streamer=streamer,
stopping_criteria=StoppingCriteriaList([stop]),
)
stream_complete = Event()
def generate_and_signal_complete():
m.generate(**generate_kwargs)
stream_complete.set()
def log_after_stream_complete():
stream_complete.wait()
log_conversation(
conversation_id,
history,
messages,
{
"top_k": top_k,
"top_p": top_p,
"temperature": temperature,
"repetition_penalty": repetition_penalty,
},
)
t1 = Thread(target=generate_and_signal_complete)
t1.start()
t2 = Thread(target=log_after_stream_complete)
t2.start()
# Initialize an empty string to store the generated text
partial_text = ""
for new_text in streamer:
partial_text += new_text
history[-1][1] = partial_text
yield history
def get_uuid():
return str(uuid4())
with gr.Blocks(
theme=gr.themes.Soft(),
css=".disclaimer {font-variant-caps: all-small-caps;}",
) as demo:
conversation_id = gr.State(get_uuid)
gr.Markdown(
"""<h1><center>Guanaco Demo</center></h1>
"""
)
chatbot = gr.Chatbot().style(height=500)
with gr.Row():
with gr.Column():
msg = gr.Textbox(
label="Chat Message Box",
placeholder="Chat Message Box",
show_label=False,
).style(container=False)
with gr.Column():
with gr.Row():
submit = gr.Button("Submit")
stop = gr.Button("Stop")
clear = gr.Button("Clear")
with gr.Row():
with gr.Accordion("Advanced Options:", open=False):
with gr.Row():
with gr.Column():
with gr.Row():
temperature = gr.Slider(
label="Temperature",
value=0.7,
minimum=0.0,
maximum=1.0,
step=0.1,
interactive=True,
info="Higher values produce more diverse outputs",
)
with gr.Column():
with gr.Row():
top_p = gr.Slider(
label="Top-p (nucleus sampling)",
value=0.9,
minimum=0.0,
maximum=1,
step=0.01,
interactive=True,
info=(
"Sample from the smallest possible set of tokens whose cumulative probability "
"exceeds top_p. Set to 1 to disable and sample from all tokens."
),
)
with gr.Column():
with gr.Row():
top_k = gr.Slider(
label="Top-k",
value=0,
minimum=0.0,
maximum=200,
step=1,
interactive=True,
info="Sample from a shortlist of top-k tokens — 0 to disable and sample from all tokens.",
)
with gr.Column():
with gr.Row():
repetition_penalty = gr.Slider(
label="Repetition Penalty",
value=1.1,
minimum=1.0,
maximum=2.0,
step=0.1,
interactive=True,
info="Penalize repetition — 1.0 to disable.",
)
with gr.Row():
gr.Markdown(
"Disclaimer: The model can produce factually incorrect output, and should not be relied on to produce "
"factually accurate information. The model was trained on various public datasets; while great efforts "
"have been taken to clean the pretraining data, it is possible that this model could generate lewd, "
"biased, or otherwise offensive outputs.",
elem_classes=["disclaimer"],
)
with gr.Row():
gr.Markdown(
"[Privacy policy](https://gist.github.com/samhavens/c29c68cdcd420a9aa0202d0839876dac)",
elem_classes=["disclaimer"],
)
submit_event = msg.submit(
fn=user,
inputs=[msg, chatbot],
outputs=[msg, chatbot],
queue=False,
).then(
fn=bot,
inputs=[
chatbot,
temperature,
top_p,
top_k,
repetition_penalty,
conversation_id,
],
outputs=chatbot,
queue=True,
)
submit_click_event = submit.click(
fn=user,
inputs=[msg, chatbot],
outputs=[msg, chatbot],
queue=False,
).then(
fn=bot,
inputs=[
chatbot,
temperature,
top_p,
top_k,
repetition_penalty,
conversation_id,
],
outputs=chatbot,
queue=True,
)
stop.click(
fn=None,
inputs=None,
outputs=None,
cancels=[submit_event, submit_click_event],
queue=False,
)
clear.click(lambda: None, None, chatbot, queue=False)
demo.queue(max_size=128, concurrency_count=2)
# Launch your Guanaco Demo!
demo.launch()
|