README.org

GLM4

GLM-4-9B is the open-source version of the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI.

• Github
• huggingface

Running with cuda

cargo run --example glm4 --release --features cuda 

Running with cpu

cargo run --example glm4 --release -- --cpu

Output Example

cargo run  --example glm4 --release --features cuda -- --sample-len 500 --cache .
    Finished release [optimized] target(s) in 0.24s
     Running `/root/candle/target/release/examples/glm4 --sample-len 500 --cache .`
avx: true, neon: false, simd128: false, f16c: true
temp: 0.60 repeat-penalty: 1.20 repeat-last-n: 64
cache path .
retrieved the files in 6.88963ms
loaded the model in 6.113752297s
starting the inference loop
[欢迎使用GLM-4,请输入prompt]
请你告诉我什么是FFT
266 tokens generated (34.50 token/s)
Result:
。Fast Fourier Transform (FFT) 是一种快速计算离散傅里叶变换（DFT）的方法，它广泛应用于信号处理、图像处理和数据分析等领域。

具体来说，FFT是一种将时域数据转换为频域数据的算法。在数字信号处理中，我们通常需要知道信号的频率成分，这就需要进行傅立叶变换。传统的傅立叶变换的计算复杂度较高，而 FFT 则大大提高了计算效率，使得大规模的 DFT 换成为可能。

以下是使用 Python 中的 numpy 进行 FFT 的简单示例：

```python
import numpy as np

# 创建一个时域信号
t = np.linspace(0, 1, num=100)
f = np.sin(2*np.pi*5*t) + 3*np.cos(2*np.pi*10*t)

# 对该信号做FFT变换，并计算其幅值谱
fft_result = np.fft.fftshift(np.abs(np.fft.fft(f)))

```

在这个例子中，我们首先创建了一个时域信号 f。然后我们对这个信号进行了 FFT 换，得到了一个频域结果 fft_result。

This example will read prompt from stdin

Citation

  @misc{glm2024chatglm,
      title={ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools}, 
      author={Team GLM and Aohan Zeng and Bin Xu and Bowen Wang and Chenhui Zhang and Da Yin and Diego Rojas and Guanyu Feng and Hanlin Zhao and Hanyu Lai and Hao Yu and Hongning Wang and Jiadai Sun and Jiajie Zhang and Jiale Cheng and Jiayi Gui and Jie Tang and Jing Zhang and Juanzi Li and Lei Zhao and Lindong Wu and Lucen Zhong and Mingdao Liu and Minlie Huang and Peng Zhang and Qinkai Zheng and Rui Lu and Shuaiqi Duan and Shudan Zhang and Shulin Cao and Shuxun Yang and Weng Lam Tam and Wenyi Zhao and Xiao Liu and Xiao Xia and Xiaohan Zhang and Xiaotao Gu and Xin Lv and Xinghan Liu and Xinyi Liu and Xinyue Yang and Xixuan Song and Xunkai Zhang and Yifan An and Yifan Xu and Yilin Niu and Yuantao Yang and Yueyan Li and Yushi Bai and Yuxiao Dong and Zehan Qi and Zhaoyu Wang and Zhen Yang and Zhengxiao Du and Zhenyu Hou and Zihan Wang},
      year={2024},
      eprint={2406.12793},
      archivePrefix={arXiv},
      primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}
}

    @misc{wang2023cogvlm,
      title={CogVLM: Visual Expert for Pretrained Language Models}, 
      author={Weihan Wang and Qingsong Lv and Wenmeng Yu and Wenyi Hong and Ji Qi and Yan Wang and Junhui Ji and Zhuoyi Yang and Lei Zhao and Xixuan Song and Jiazheng Xu and Bin Xu and Juanzi Li and Yuxiao Dong and Ming Ding and Jie Tang},
      year={2023},
      eprint={2311.03079},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}