更新chatglm3-6b-int4.flm的简介
Browse files
README.md
CHANGED
@@ -10,4 +10,33 @@ tags:
|
|
10 |
- torch2flm
|
11 |
- python
|
12 |
- chinese
|
13 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
- torch2flm
|
11 |
- python
|
12 |
- chinese
|
13 |
+
---
|
14 |
+
## 介绍 (Introduction)
|
15 |
+
ChatGLM3-6B 是 ChatGLM 系列最新一代的开源模型,在保留了前两代模型对话流畅、部署门槛低等众多优秀特性的基础上,ChatGLM3-6B 引入了如下特性:
|
16 |
+
|
17 |
+
1. **更强大的基础模型:** ChatGLM3-6B 的基础模型 ChatGLM3-6B-Base 采用了更多样的训练数据、更充分的训练步数和更合理的训练策略。在语义、数学、推理、代码、知识等不同角度的数据集上测评显示,ChatGLM3-6B-Base 具有在 10B 以下的预训练模型中最强的性能。
|
18 |
+
2. **更完整的功能支持:** ChatGLM3-6B 采用了全新设计的 [Prompt 格式](https://github.com/THUDM/ChatGLM3/blob/main/PROMPT.md),除正常的多轮对话外。同时原生支持[工具调用](https://github.com/THUDM/ChatGLM3/blob/main/tool_using/README.md)(Function Call)、代码执行(Code Interpreter)和 Agent 任务等复杂场景。
|
19 |
+
3. **更全面的开源序列:** 除了对话模型 ChatGLM3-6B 外,还开源了基础模型 ChatGLM-6B-Base、长文本对话模型 ChatGLM3-6B-32K。以上所有权重对学术研究**完全开放**,在填写[问卷](https://open.bigmodel.cn/mla/form)进行登记后**亦允许免费商业使用**。
|
20 |
+
|
21 |
+
ChatGLM3-6B is the latest open-source model in the ChatGLM series. While retaining many excellent features such as smooth dialogue and low deployment threshold from the previous two generations, ChatGLM3-6B introduces the following features:
|
22 |
+
|
23 |
+
1. **More Powerful Base Model:** The base model of ChatGLM3-6B, ChatGLM3-6B-Base, employs a more diverse training dataset, more sufficient training steps, and a more reasonable training strategy. Evaluations on datasets such as semantics, mathematics, reasoning, code, knowledge, etc., show that ChatGLM3-6B-Base has the strongest performance among pre-trained models under 10B.
|
24 |
+
2. **More Comprehensive Function Support:** ChatGLM3-6B adopts a newly designed [Prompt format](https://github.com/THUDM/ChatGLM3/blob/main/PROMPT_en.md), in addition to the normal multi-turn dialogue. It also natively supports [function call](https://github.com/THUDM/ChatGLM3/blob/main/tool_using/README_en.md), code interpreter, and complex scenarios such as agent tasks.
|
25 |
+
3. **More Comprehensive Open-source Series:** In addition to the dialogue model ChatGLM3-6B, the base model ChatGLM-6B-Base and the long-text dialogue model ChatGLM3-6B-32K are also open-sourced. All the weights are **fully open** for academic research, and after completing the [questionnaire](https://open.bigmodel.cn/mla/form) registration, they are also **allowed for free commercial use**.
|
26 |
+
|
27 |
+
## 软件依赖 (Dependencies)
|
28 |
+
|
29 |
+
## 引用 https://wtl4it.blog.csdn.net/article/details/137183330
|
30 |
+
```shell
|
31 |
+
cd fastllm
|
32 |
+
mkdir build
|
33 |
+
cd build
|
34 |
+
cmake .. -DUSE_CUDA=ON # 如果不使用GPU编译,那么使用 cmake .. -DUSE_CUDA=OFF
|
35 |
+
make -j
|
36 |
+
|
37 |
+
./main -p ~/chatglm3-6b-int4.flm
|
38 |
+
```
|
39 |
+
|
40 |
+
|
41 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6455fc13aaaf85a98fa950c7/iE5hr9VgBwmvMnHkQ7Ywd.png)
|
42 |
+
|