Home Explore Help
Register Sign In
github
/
GLM-130B
mirror of https://github.com/THUDM/GLM-130B.git
2
0
Fork 0
Files Issues 0 Wiki
Browse Source

Update README.md

Shaw 3 years ago
parent
a361c5c843
commit
b1fb318cf4
1 changed files with 2 additions and 0 deletions
Unified View Show Diff Stats
  1. 2 0
      README.md

+ 2 - 0
README.md
View File 

@@ -16,6 +16,8 @@ GLM-130B is an open bilingual (English & Chinese) bidirectional dense model with
 
 - **Reproducibility:** all results (30+ tasks) can be easily reproduced with open-sourced code and model checkpoints.

 - **Reproducibility:** all results (30+ tasks) can be easily reproduced with open-sourced code and model checkpoints.

 - **Cross-Platform:** supports training and inference on NVIDIA, Hygon DCU, Ascend 910, and Sunway (Will be released soon).

 - **Cross-Platform:** supports training and inference on NVIDIA, Hygon DCU, Ascend 910, and Sunway (Will be released soon).

 

 

+If you find our work and our open-sourced model useful, starring our repo to encourage our following development! :)

+

 ## News

 ## News

 

 

 - 🌟 **[2022.08.24]** We are proud to publish the quantized version for GLM-130B.  While preserving the activation precision as FP16, the model weights can be quantized to as low as **INT4 with almost no degradation of performance**, further reducing the hardware requirements of the GLM-130B to **a single server with 4 * RTX 3090 (24G)**! See [Quantization of GLM-130B](docs/quantization.md) for details.

 - 🌟 **[2022.08.24]** We are proud to publish the quantized version for GLM-130B.  While preserving the activation precision as FP16, the model weights can be quantized to as low as **INT4 with almost no degradation of performance**, further reducing the hardware requirements of the GLM-130B to **a single server with 4 * RTX 3090 (24G)**! See [Quantization of GLM-130B](docs/quantization.md) for details.