Self-Instruct构造Prompt的例子

  1. 人工构造一批Prompt做种子。(Starting with a small seed set of human-written tasks)
  2. 每次把一些种子+后来生成的Prompt,放到Input里做few-shot examples,用LLM生成更多的Prompt;(Using the LLM to generate new instructions based on the seed tasks)
  3. 过滤掉质量太差的,修正能要的;(Filtering and refining the generated instructions)
  4. 把生成的所有Prompt,输入LLM得到输出结果;(Creating input-output instances for the new instructions)
  5. Input+Output,做LLM的训练样本(Using the generated dataset to fine-tune the LLM)

第2步,LLM生成:

复制代码
import random
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load a pre-trained language model
model_name = "bigcode/starcoderbase-1b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Seed tasks (simplified for demonstration)
seed_tasks = [
    "Write a function to calculate the factorial of a number.",
    "Create a class to represent a bank account.",
    "Implement a binary search algorithm."
]

def generate_instruction(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=50)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

def self_instruct(num_iterations):
    generated_tasks = []
    
    for _ in range(num_iterations):
        # Sample existing tasks
        sampled_tasks = random.sample(seed_tasks + generated_tasks, min(3, len(seed_tasks) + len(generated_tasks)))
        
        # Create a prompt for generating new instructions
        prompt = "Generate a new programming task based on these examples:\n\n"
        prompt += "\n".join(sampled_tasks)
        prompt += "\n\nNew task:"
        
        # Generate a new instruction
        new_task = generate_instruction(prompt)
        
        # In practice, you would filter and refine the generated task here
        
        generated_tasks.append(new_task)
    
    return generated_tasks

# Run Self-Instruct
new_tasks = self_instruct(5)
for i, task in enumerate(new_tasks, 1):
    print(f"Task {i}: {task}")

第3步过滤:

人工定义一些规则,过滤掉太差的;(也可以用LLM来做裁判)

目的:确保质量和多样性;

  • Filter out instructions that are too short or too long
  • Filter out instructions containing keywords unsuitable for language models (e.g. "image", "graph", "file", "plot")
  • Filter out instructions starting with punctuation
  • Filter out instructions starting with non-English characters
  • Filter out instructions that have high ROUGE-L similarity (above 0.7) with any existing instruction in the task pool
相关推荐
视觉语言导航2 小时前
ICCV-2025 | 复杂场景的精准可控生成新突破!基于场景图的可控 3D 户外场景生成
人工智能·深度学习·具身智能
AI街潜水的八角4 小时前
深度学习图像分类数据集—濒危动物识别分类
人工智能·深度学习
安思派Anspire4 小时前
LangGraph + MCP + Ollama:构建强大代理 AI 的关键(一)
前端·深度学习·架构
FF-Studio5 小时前
大语言模型(LLM)课程学习(Curriculum Learning)、数据课程(data curriculum)指南:从原理到实践
人工智能·python·深度学习·神经网络·机器学习·语言模型·自然语言处理
CoovallyAIHub5 小时前
YOLO模型优化全攻略:从“准”到“快”,全靠这些招!
深度学习·算法·计算机视觉
G.E.N.7 小时前
开源!RAG竞技场(2):标准RAG算法
大数据·人工智能·深度学习·神经网络·算法·llm·rag
zm-v-159304339869 小时前
ArcGIS 水文分析升级:基于深度学习的流域洪水演进过程模拟
人工智能·深度学习·arcgis
SHIPKING39311 小时前
【机器学习&深度学习】什么是下游任务模型?
人工智能·深度学习·机器学习
伍哥的传说16 小时前
React 各颜色转换方法、颜色值换算工具HEX、RGB/RGBA、HSL/HSLA、HSV、CMYK
深度学习·神经网络·react.js
要努力啊啊啊18 小时前
YOLOv3-SPP Auto-Anchor 聚类调试指南!
人工智能·深度学习·yolo·目标检测·目标跟踪·数据挖掘