Jerydeak commited on
Commit
f89b4fc
1 Parent(s): c656177

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -5
README.md CHANGED
@@ -19,7 +19,7 @@ tags:
19
  📍Experience the larger-scale ChatGLM model at <a href="https://www.chatglm.cn">chatglm.cn</a>
20
  </p>
21
 
22
- ## 介绍
23
  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:
24
 
25
  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。
@@ -28,16 +28,26 @@ ChatGLM3-6B 是 ChatGLM 系列最新一代的开源模型,在保留了前两
28
 
29
  本仓库为 ChatGLM3-6B 的基础模型 ChatGLM3-6B-Base。
30
 
31
- ## 软件依赖
 
 
 
 
 
 
 
 
32
 
33
  ```shell
34
  pip install protobuf transformers==4.30.2 cpm_kernels torch>=2.0 gradio mdtex2html sentencepiece accelerate
35
  ```
36
 
37
- ## 代码调用
38
 
39
  作为没有经过人类意图对齐的模型,ChatGLM3-6B-Base 不能用于多轮对话。但是可以进行文本续写。
40
 
 
 
41
  ```python
42
  from transformers import AutoTokenizer, AutoModel
43
  tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm3-6b-base", trust_remote_code=True)
@@ -53,14 +63,18 @@ print(tokenizer.decode(outputs[0].tolist()))
53
  For more instructions, including how to run CLI and web demos, and model quantization, please refer to our [Github Repo](https://github.com/THUDM/ChatGLM).
54
 
55
 
56
- ## 协议
57
 
58
  本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源,ChatGLM3-6B 模型的权重的使用则需要遵循 [Model License](MODEL_LICENSE)。
59
 
60
- ## 引用
 
 
61
 
62
  如果你觉得我们的工作有帮助的话,请考虑引用下列论文。
63
 
 
 
64
  ```
65
  @article{zeng2022glm,
66
  title={Glm-130b: An open bilingual pre-trained model},
 
19
  📍Experience the larger-scale ChatGLM model at <a href="https://www.chatglm.cn">chatglm.cn</a>
20
  </p>
21
 
22
+ ## 介绍 (introduction)
23
  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:
24
 
25
  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。
 
28
 
29
  本仓库为 ChatGLM3-6B 的基础模型 ChatGLM3-6B-Base。
30
 
31
+ 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:
32
+
33
+ 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.
34
+ 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.
35
+ 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**.
36
+
37
+ This repo is ChatGLM3-6B-Base, the base model of ChatGLM3-6B.
38
+
39
+ ## 软件依赖 (Dependencies)
40
 
41
  ```shell
42
  pip install protobuf transformers==4.30.2 cpm_kernels torch>=2.0 gradio mdtex2html sentencepiece accelerate
43
  ```
44
 
45
+ ## 代码调用 (Code Usage)
46
 
47
  作为没有经过人类意图对齐的模型,ChatGLM3-6B-Base 不能用于多轮对话。但是可以进行文本续写。
48
 
49
+ As a model that has not been aligned with human intent, ChatGLM3-6B-Base cannot be used for multi-turn conversations. However, text completion is possible.
50
+
51
  ```python
52
  from transformers import AutoTokenizer, AutoModel
53
  tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm3-6b-base", trust_remote_code=True)
 
63
  For more instructions, including how to run CLI and web demos, and model quantization, please refer to our [Github Repo](https://github.com/THUDM/ChatGLM).
64
 
65
 
66
+ ## 协议 (License)
67
 
68
  本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源,ChatGLM3-6B 模型的权重的使用则需要遵循 [Model License](MODEL_LICENSE)。
69
 
70
+ The code in this repository is open-sourced under the [Apache-2.0 license](LICENSE), while the use of the ChatGLM3-6B model weights needs to comply with the [Model License](MODEL_LICENSE).
71
+
72
+ ## 引用 (Citation)
73
 
74
  如果你觉得我们的工作有帮助的话,请考虑引用下列论文。
75
 
76
+ If you find our work helpful, please consider citing the following papers.
77
+
78
  ```
79
  @article{zeng2022glm,
80
  title={Glm-130b: An open bilingual pre-trained model},