File size: 1,618 Bytes
50e7f42 0a39f44 50e7f42 9d139d0 0a39f44 50e7f42 |
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 |
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
from threading import Thread
import bitsandbytes
tokenizer = AutoTokenizer.from_pretrained("./model/")
model = AutoModelForCausalLM.from_pretrained("./model/", device_map="auto", load_in_4bit=True)
model = model.to('cuda:0')
class StopOnTokens(StoppingCriteria):
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
stop_ids = [29, 0]
for stop_id in stop_ids:
if input_ids[0][-1] == stop_id:
return True
return False
def chat(message, history):
history_transformer_format = history + [[message, ""]]
stop = StopOnTokens()
messages = "".join("".join(["/n<human>:"+item[0], "/n<bot>:"+item[1]]) for item in history_transformer_format)
model_inputs = tokenizer([messages], return_tensors="pt").to('cuda')
streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
generate_kwargs = dict(
model_inputs,
streamer=streamer,
max_new_tokens=1024,
do_sample=True,
top_p=0.95,
top_k=1000,
temperature=1.0,
num_beams=1,
stopping_criteria=StoppingCriteriaList([stop])
)
t = Thread(target=model.generate, kwargs=generate_kwargs)
t.start()
partial_message = ""
for new_token in streamer:
if new_token != '<':
partial_message += new_token
yield partial_message
gr.ChatInterface(chat).launch()
|