OpenNLPLab commited on
Commit
8499a6e
1 Parent(s): 590b4b9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -26,7 +26,7 @@ This official repository unveils the TransNormerLLM3 model along with its open-s
26
  - **TransNormerLLM3-15B** is purely intergrated with **[Lightning Attention-2](http://arxiv.org/abs/2401.04658)**, which can maintain a **stable TGS** during training of **unlimited sequence lengths**, up until encountering firm limitations like GPU memory constraints.
27
  - **Titoken** tokenizer is used with a total **vocabulary size** of about **100,000**.
28
  <p align="center">
29
- <img src="./images/TransNormer3.jpg" width="75%" />
30
  </p>
31
 
32
  ### Pre-training Logbook
@@ -96,6 +96,6 @@ If you wish to cite our work, please use the following reference:
96
  ```
97
 
98
  <p align="center">
99
- <img src="./images/lightning3-leopard.jpg" width="67%" />
100
  - OpenNLPLab @2024 -
101
  </p>
 
26
  - **TransNormerLLM3-15B** is purely intergrated with **[Lightning Attention-2](http://arxiv.org/abs/2401.04658)**, which can maintain a **stable TGS** during training of **unlimited sequence lengths**, up until encountering firm limitations like GPU memory constraints.
27
  - **Titoken** tokenizer is used with a total **vocabulary size** of about **100,000**.
28
  <p align="center">
29
+ <img src="./images/TransNormer3.jpg" width="65%" />
30
  </p>
31
 
32
  ### Pre-training Logbook
 
96
  ```
97
 
98
  <p align="center">
99
+ <img src="./images/lightning3-leopard.jpg" width="50%" />
100
  - OpenNLPLab @2024 -
101
  </p>