File size: 2,439 Bytes
75ea2b2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from threading import Thread
from typing import Iterator

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer

# Original version
model_id = "LinkSoul/Chinese-Llama-2-7b"
# 4 bit version
# model_id = "LinkSoul/Chinese-Llama-2-7b-4bit"

if torch.cuda.is_available():
    if model_id.endswith("4bit"):
        model = AutoModelForCausalLM.from_pretrained(
                model_id,
                load_in_4bit=True,
                torch_dtype=torch.float16,
                device_map='auto'
            )
    else:
        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'[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n']
    for user_input, response in chat_history:
        texts.append(f'{user_input.strip()} [/INST] {response.strip()} </s><s> [INST] ')
    texts.append(f'{message.strip()} [/INST]')
    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')['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').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)