File size: 2,922 Bytes
89fcef4 c2f0918 89fcef4 3d274b3 c2f0918 db3180b c2f0918 89fcef4 c2f0918 89fcef4 c2f0918 89fcef4 c2f0918 89fcef4 c2f0918 89fcef4 |
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 |
from threading import Thread
from typing import Iterator
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
print(f"Is CUDA available: {torch.cuda.is_available()}")
print(f"{torch.cuda.current_device()}")
print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")
model_id = "TheBloke/Chronos-Beluga-v2-13B-GPTQ"
tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
model = AutoGPTQForCausalLM.from_quantized(model_id,
use_safetensors=True,
trust_remote_code=False,
device="cuda:0",
use_triton=False,
quantize_config=None)
# model_id = 'meta-llama/Llama-2-7b-chat-hf'
# if torch.cuda.is_available():
# model = AutoModelForCausalLM.from_pretrained(
# model_id,
# torch_dtype=torch.float16,
# device_map='auto'
# )
# else:
# model = None
# tokenizer = AutoTokenizer.from_pretrained(model_id)
def get_prompt(message: str, chat_history: list[tuple[str, str]],
system_prompt: str) -> str:
# texts = [f'<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n']
texts = [f'{system_prompt}\n\n']
# The first user input is _not_ stripped
do_strip = False
for user_input, response in chat_history:
user_input = user_input.strip() if do_strip else user_input
do_strip = True
texts.append(f'{user_input} {response.strip()} ')
message = message.strip() if do_strip else message
texts.append(f'{message}')
return ''.join(texts)
def get_input_token_length(message: str, chat_history: list[tuple[str, str]], system_prompt: str) -> int:
prompt = get_prompt(message, chat_history, system_prompt)
input_ids = tokenizer([prompt], return_tensors='np', add_special_tokens=False)['input_ids']
return input_ids.shape[-1]
def run(message: str,
chat_history: list[tuple[str, str]],
system_prompt: str,
max_new_tokens: int = 1024,
temperature: float = 0.8,
top_p: float = 0.95,
top_k: int = 50) -> Iterator[str]:
prompt = get_prompt(message, chat_history, system_prompt)
inputs = tokenizer([prompt], return_tensors='pt', add_special_tokens=False).to('cuda')
streamer = TextIteratorStreamer(tokenizer,
timeout=10.,
skip_prompt=True,
skip_special_tokens=True)
generate_kwargs = dict(
inputs,
streamer=streamer,
max_new_tokens=max_new_tokens,
do_sample=True,
top_p=top_p,
top_k=top_k,
temperature=temperature,
num_beams=1,
)
t = Thread(target=model.generate, kwargs=generate_kwargs)
t.start()
outputs = []
for text in streamer:
outputs.append(text)
yield ''.join(outputs)
|