更强大的性能：基于 ChatGLM 初代模型的开发经验，我们全面升级了 ChatGLM2-6B 的基座模型。ChatGLM2-6B 使用了 GLM 的混合目标函数，经过了 1.4T 中英标识符的预训练与人类偏好对齐训练，评测结果显示，相比于初代模型，ChatGLM2-6B 在 MMLU（+23%）、CEval（+33%）、GSM8K（+571%）、BBH（+60%）等数据集上的性能取得了大幅度的提升，在同尺寸开源模型中具有较强的竞争力。
更长的上下文：基于 FlashAttention 技术，我们将基座模型的上下文长度（Context Length）由 ChatGLM-6B 的 2K 扩展到了 32K，并在对话阶段使用 8K 的上下文长度训练，允许更多轮次的对话。但当前版本的 ChatGLM2-6B 对单轮超长文档的理解能力有限，我们会在后续迭代升级中着重进行优化。
更高效的推理：基于 Multi-Query Attention 技术，ChatGLM2-6B 有更高效的推理速度和更低的显存占用：在官方的模型实现下，推理速度相比初代提升了 42%，INT4 量化下，6G 显存支持的对话长度由 1K 提升到了 8K。

ChatGLM2-6B is the second-generation version of the open-source bilingual (Chinese-English) chat model ChatGLM-6B. It retains the smooth conversation flow and low deployment threshold of the first-generation model, while introducing the following new features:

Stronger Performance: Based on the development experience of the first-generation ChatGLM model, we have fully upgraded the base model of ChatGLM2-6B. ChatGLM2-6B uses the hybrid objective function of GLM, and has undergone pre-training with 1.4T bilingual tokens and human preference alignment training. The evaluation results show that, compared to the first-generation model, ChatGLM2-6B has achieved substantial improvements in performance on datasets like MMLU (+23%), CEval (+33%), GSM8K (+571%), BBH (+60%), showing strong competitiveness among models of the same size.
Longer Context: Based on FlashAttention technique, we have extended the context length of the base model from 2K in ChatGLM-6B to 32K, and trained with a context length of 8K during the dialogue alignment, allowing for more rounds of dialogue. However, the current version of ChatGLM2-6B has limited understanding of single-round ultra-long documents, which we will focus on optimizing in future iterations.
More Efficient Inference: Based on Multi-Query Attention technique, ChatGLM2-6B has more efficient inference speed and lower GPU memory usage: under the official implementation, the inference speed has increased by 42% compared to the first generation; under INT4 quantization, the dialogue length supported by 6G GPU memory has increased from 1K to 8K.

软件依赖

pip install protobuf transformers==4.30.2 cpm_kernels torch>=2.0 gradio mdtex2html sentencepiece accelerate

代码调用

可以通过如下代码调用 ChatGLM-6B 模型来生成对话：

python

from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True).half().cuda()
model = model.eval()
response, history = model.chat(tokenizer, "你好", history=[])
response

关于更多的使用说明，包括如何运行命令行和网页版本的 DEMO，以及使用模型量化以节省显存，请参考我们的 Github Repo。

For more instructions, including how to run CLI and web demos, and model quantization, please refer to our Github Repo.

Change Log

v1.0

协议

本仓库的代码依照 Apache-2.0 协议开源，ChatGLM2-6B 模型的权重的使用则需要遵循 Model License。

引用

如果你觉得我们的工作有帮助的话，请考虑引用下列论文，ChatGLM2-6B 的论文会在近期公布，尽情期待～

@article{zeng2022glm,
  title={Glm-130b: An open bilingual pre-trained model},
  author={Zeng, Aohan and Liu, Xiao and Du, Zhengxiao and Wang, Zihan and Lai, Hanyu and Ding, Ming and Yang, Zhuoyi and Xu, Yifan and Zheng, Wendi and Xia, Xiao and others},
  journal={arXiv preprint arXiv:2210.02414},
  year={2022}
}

@inproceedings{du2022glm,
  title={GLM: General Language Model Pretraining with Autoregressive Blank Infilling},
  author={Du, Zhengxiao and Qian, Yujie and Liu, Xiao and Ding, Ming and Qiu, Jiezhong and Yang, Zhilin and Tang, Jie},
  booktitle={Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  pages={320--335},
  year={2022}
}

Ian-14/llm13

ChatGLM2-6B

介绍

软件依赖

代码调用

Change Log

协议

引用

Ian-14/
llm13