🚀 SocraticLM模型

SocraticLM是一个基于Qwen2.5-Math-7B-Instruct微调的模型，专为教育场景设计。它能以苏格拉底式引导帮助学生解决数学问题，也可直接解答数学问题，支持中英文。

🚀 快速开始

模型简介

本模型是在Qwen2.5-Math-7B-Instruct基础上，使用SocraTeach数据集进行微调得到的，是SocraticLM的具体实现。

预期用途与限制

SocraticLM主要用于教育场景，当学生在学习解决数学问题遇到困难时，它能提供苏格拉底式的引导。同时，该模型也可以直接解决数学问题。此模型主要支持英文和中文。

安装指南

此部分文档未提及具体安装步骤，因此跳过该章节。

💻 使用示例

基础用法

使用Huggingface transformers库

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CogBase-USTC/SocraticLM")
model = AutoModelForCausalLM.from_pretrained(
    "CogBase-USTC/SocraticLM",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

### 数学问题求解 ###
messages = [
    {"role": "system", "content" : "Please analyse and solve the following problem step by step."},
    {"role": "user", "content": "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May?"},
]

### 苏格拉底式引导 ###
# messages = [
#     {"role": "system", "content" : "You are a Socratic teacher, please guide me to solve the [Problem] with heuristic questions based on the following information. \n"},
#     {"role": "user", "content": "[Problem] Debelyn, Christel, and Andrena collect dolls. Debelyn had 20 dolls before she gave Andrena 2 dolls. Christel had 24 dolls before giving Andrena 5 dolls. After all the gifts, Andrena now has 2 more dolls  than Christel, how many more dolls does andrena have now than Debelyn? [Answer] 3 [Analysis] Debelyn had 20 - 2 = 18 dolls left after giving out 2 dolls to Christel. Christel had 24 + 2 = 26 dolls after receiving 2 dolls from Debelyn. Christel had 24 - 5 = 19 dolls after giving Andrena 5 dolls. So, Andrena has 19 +2 = 21 dolls now. Therefore, Andrena has 21 - 18 = 3 more dolls than Debelyn."},
# ]

prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

inputs = tokenizer.encode(prompt, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=4096)
print(tokenizer.decode(outputs[0]))

使用vLLM库

from vllm import LLM, SamplingParams

llm = LLM(model=r'CogBase-USTC/SocraticLM',
          tokenizer=r'CogBase-USTC/SocraticLM',
          trust_remote_code=True,
          tensor_parallel_size=1,
          gpu_memory_utilization=0.99,
          enable_chunked_prefill=True,
          max_num_batched_tokens=512,
          max_num_seqs=128)
sampling_params = SamplingParams(temperature=0, max_tokens=4096, seed=42)


def print_outputs(outputs):
    for output in outputs:
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"Generated text: {generated_text!r}")
    print("-" * 80)


print("=" * 80)

### 数学问题求解 ###
conversation = [
    {
        "role": "system",
        "content": "Please analyse and solve the following problem step by step."
    },
    {
        "role": "user", 
        "content": "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May?"
    },
]

### 苏格拉底式引导 ###
# conversation = [
#     {
#         "role": "system",
#         "content": "You are a Socratic teacher, please guide me to solve the [Problem] with heuristic questions based on the following information. \n"
#     },
#     {
#         "role": "user", 
#         "content": "[Problem] Debelyn, Christel, and Andrena collect dolls. Debelyn had 20 dolls before she gave Andrena 2 dolls. Christel had 24 dolls before giving Andrena 5 dolls. After all the gifts, Andrena now has 2 more dolls  than Christel, how many more dolls does andrena have now than Debelyn? [Answer] 3 [Analysis] Debelyn had 20 - 2 = 18 dolls left after giving out 2 dolls to Christel. Christel had 24 + 2 = 26 dolls after receiving 2 dolls from Debelyn. Christel had 24 - 5 = 19 dolls after giving Andrena 5 dolls. So, Andrena has 19 +2 = 21 dolls now. Therefore, Andrena has 21 - 18 = 3 more dolls than Debelyn."
#     },
# ]

outputs = llm.chat(conversation,
                   sampling_params=sampling_params,
                   use_tqdm=False,
                )
print_outputs(outputs)

详细文档

训练超参数

训练过程中使用的超参数如下：

• 学习率（learning_rate）：1e-05
• 训练批次大小（train_batch_size）：8
• 随机种子（seed）：42
• 分布式类型（distributed_type）：多GPU
• 设备数量（num_devices）：4
• 总训练批次大小（total_train_batch_size）：32
• 总评估批次大小（total_eval_batch_size）：32
• 优化器（optimizer）：使用OptimizerNames.ADAMW_TORCH，其中beta1=0.9，beta2=0.999，epsilon=1e-08，无额外优化器参数
• 学习率调度器类型（lr_scheduler_type）：余弦
• 学习率调度器热身步数（lr_scheduler_warmup_steps）：20

框架版本

• Transformers：4.46.2
• Pytorch：2.5.1+cu124
• Datasets：3.1.0
• Tokenizers：0.20.3

📄 许可证

许可证类型：其他（other）