mirror of https://github.com/InternLM/InternLM
92 lines
4.0 KiB
Markdown
92 lines
4.0 KiB
Markdown
# InternLM-Chat 智能体
|
||
|
||
[English](README.md) | 简体中文
|
||
|
||
## 简介
|
||
|
||
InternLM2.5-Chat 在代码解释和通用工具调用方面的能力得到进一步提升。基于更强和更具有泛化性的指令理解、工具筛选与结果反思等能力，新版模型可以更可靠地支持复杂智能体的搭建，支持对工具进行有效的多轮调用，完成较复杂的任务。在配合代码解释器（code-interpreter）的条件下，InternLM2.5-Chat 在 MATH 上可以达到和 GPT-4 相仿的水平。基于在数理和工具方面强大的基础能力，InternLM2.5-Chat 提供了实用的数据分析能力。
|
||
|
||
以下是 InternLM2.5-Chat 在数学代码解释器上的结果。
|
||
|
||
| 模型 | 是否集成工具 | MATH |
|
||
| :-----------------: | :----------: | :--: |
|
||
| InternLM2-Chat-7B | w/ | 45.1 |
|
||
| InternLM2-Chat-20B | w/ | 51.2 |
|
||
| InternLM2.5-7B-Chat | w/ | 63.0 |
|
||
| gpt-4-0125-preview | w/o | 64.2 |
|
||
|
||
## 体验
|
||
|
||
我们提供了使用 [Lagent](lagent_zh-CN.md) 来基于 InternLM2.5-Chat 构建智能体调用代码解释器的例子。首先安装额外依赖：
|
||
|
||
```bash
|
||
pip install -r requirements.txt
|
||
```
|
||
|
||
运行以下脚本在 MATH 测试集上进行推理和评估：
|
||
|
||
```bash
|
||
python streaming_inference.py \
|
||
--backend=lmdeploy \ # For HuggingFace models: hf
|
||
--model_path=internlm/internlm2_5-7b-chat \
|
||
--tp=1 \
|
||
--temperature=1.0 \
|
||
--top_k=1 \
|
||
--output_path=math_lmdeploy.jsonl \
|
||
--do_eval
|
||
```
|
||
|
||
`output_path` 是一个存储推理结果的 jsonl 格式文件，每行形如：
|
||
|
||
````json
|
||
{
|
||
"problem": "The midpoint of the line segment between $(x,y)$ and $(2,4)$ is $(-7,0)$. Find $(x,y)$.",
|
||
"level": "Level 3",
|
||
"type": "Algebra",
|
||
"solution": "Applying the midpoint formula gives $$\\left(\\frac{2+x}{2},\\frac{4+y}{2}\\right)=(-7,0).$$Solving $\\frac{2+x}{2}=-7$ for $x$ and $\\frac{4+y}{2} = 0$ for $y$ we find $(x,y)$ to be $\\boxed{(-16,-4)}$.",
|
||
"idx": 306,
|
||
"query": "The midpoint of the line segment between $(x,y)$ and $(2,4)$ is $(-7,0)$. Find $(x,y)$.",
|
||
"gt": "(-16,-4)",
|
||
"pred": [
|
||
"(-16,-4)"
|
||
],
|
||
"steps": [
|
||
{
|
||
"role": "language",
|
||
"content": "To find the coordinates of the point $(x,y)$, we can use the midpoint formula. The midpoint $M$ of a line segment with endpoints $(x_1, y_1)$ and $(x_2, y_2)$ is given by:\n\n\\[M = \\left(\\frac{x_1 + x_2}{2}, \\frac{y_1 + y_2}{2}\\right)\\]\n\nGiven that the midpoint is $(-7,0)$ and one endpoint is $(2,4)$, we can set up equations to solve for $x$ and $y$.\n\nLet's start by setting up the equations based on the midpoint formula:\n\n\\[\\frac{x + 2}{2} = -7\\]\n\\[\\frac{y + 4}{2} = 0\\]\n\nNow, let's solve these equations using Python to find the values of $x$ and $y$."
|
||
},
|
||
{
|
||
"role": "tool",
|
||
"content": {
|
||
"name": "AsyncIPythonInteractiveManager",
|
||
"parameters": {
|
||
"command": "```python\nfrom sympy import symbols, Eq, solve\n\n# Define symbols\nx, y = symbols('x y')\n\n# Define equations based on the midpoint formula\neq1 = Eq((x + 2)/2, -7)\neq2 = Eq((y + 4)/2, 0)\n\n# Solve equations\nsolution = solve((eq1, eq2), (x, y))\n\nsolution\n```"
|
||
}
|
||
},
|
||
"name": "interpreter"
|
||
},
|
||
{
|
||
"role": "environment",
|
||
"content": "{x: -16, y: -4}",
|
||
"name": "interpreter"
|
||
},
|
||
{
|
||
"role": "language",
|
||
"content": "After solving the equations, we find that the coordinates of the point $(x,y)$ are $(-16, -4)$. Therefore, the solution to the problem is:\n\n\\[\\boxed{(-16, -4)}\\]"
|
||
}
|
||
],
|
||
"error": null
|
||
}
|
||
````
|
||
|
||
如果已经准备好了该文件，可直接跳过推理阶段进行评估：
|
||
|
||
```bash
|
||
python streaming_inference.py \
|
||
--output_path=math_lmdeploy.jsonl \
|
||
--no-do_infer \
|
||
--do_eval
|
||
```
|
||
|
||
请参考 [`streaming_inference.py`](streaming_inference.py) 获取更多关于参数的信息。
|