介绍

个人感受

如何使用

from transformers import AutoModelForCausalLM, AutoTokenizer


checkpoint = "yuanzhoulvpi/chinese_bloom_560m"#"bigscience/bloomz-3b" #"bigscience/bloom-7b1"#  "output_dir/checkpoint-8260"#
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint)

PROMPT_DICT = {
    "prompt_input": (
        "Below is an instruction that describes a task, paired with an input that provides further context. "
        "Write a response that appropriately completes the request.\n\n"
        "### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:"
    ),
    "prompt_no_input": (
        "Below is an instruction that describes a task. "
        "Write a response that appropriately completes the request.\n\n"
        "### Instruction:\n{instruction}\n\n### Response:"
    ),
}

from typing import Optional
def generate_input(instruction:Optional[str]= None, input_str:Optional[str] = None) -> str:
    if input_str is None:
        return PROMPT_DICT['prompt_no_input'].format_map({'instruction':instruction})
    else:
        return PROMPT_DICT['prompt_input'].format_map({'instruction':instruction, 'input':input_str})


for i in range(5):
    print("*"*80)

    inputs = tokenizer.encode(generate_input(instruction="你是谁"), return_tensors="pt")
    outputs = model.generate(inputs,num_beams=3,
                            max_new_tokens=512,
                            do_sample=False, 
                            top_k=10,
                            penalty_alpha=0.6,
                            temperature=0.8,
                            repetition_penalty=1.2)
    print(tokenizer.decode(outputs[0]))

example1

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
写一篇关于水杯的文章

### Response: 杯子是用来喝水用的</s>

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
写一篇关于水杯的文章

### Response:
水杯是人们日常生活中必不可少的物品之一，它能够帮助人们盛放、储存和运输水。以下是一些有关水杯的详细信息：
1. 形状：水杯通常有圆形、方形、长方形等不同形状。
2. 容量：水杯通常有10毫升、20毫升、30毫升、40毫升等不同容量。
3. 材质：水杯通常有玻璃、陶瓷、金属等不同材质。
4. 颜色：水杯通常有红色、蓝色、黄色、绿色等不同颜色。
5. 用途：水杯通常用于盛放、储存和运输水，如饮料、果汁、茶、咖啡等。
6. 功能：水杯可以用来盛放、储存和运输各种液体，如饮料、果汁、茶、咖啡等。
7. 用途广泛：水杯不仅用于盛放、储存和运输水，还可以用于制作各种饮料、果汁、茶、咖啡等。
总之，水杯是一个不可或缺的物品，它能够帮助人们盛放、储存和运输水，同时还可以用于制作各种饮料、果汁、茶、咖啡等。</s>

example 2

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
你是谁

### Response: I am a student.</s>

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
你是谁

### Response:我是一个AI语言模型，没有个人身份。</s>