Update README.md
Browse files
README.md
CHANGED
|
@@ -5,10 +5,6 @@ tags:
|
|
| 5 |
- LLM
|
| 6 |
- ChatGLM6B
|
| 7 |
---
|
| 8 |
-
## New Features (2023-06-20)
|
| 9 |
-
- We now support cuda version of both 11.X and 12.X
|
| 10 |
-
- lyraChatGLM has been further optimized, with faster model load speed from few minutes to less than 10s for non-int8 mode, and around 1 min for int8 mode!
|
| 11 |
-
|
| 12 |
## Breakings!
|
| 13 |
|
| 14 |
**We know what you want, and here you go!**
|
|
@@ -26,6 +22,10 @@ P.S. Recently we have received a lot of inquiries on accelerating customized mod
|
|
| 26 |
|
| 27 |
****
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
## Model Card for lyraChatGLM
|
| 30 |
|
| 31 |
lyraChatGLM is currently the **fastest ChatGLM-6B** available. To the best of our knowledge, it is the **first accelerated version of ChatGLM-6B**.
|
|
|
|
| 5 |
- LLM
|
| 6 |
- ChatGLM6B
|
| 7 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
## Breakings!
|
| 9 |
|
| 10 |
**We know what you want, and here you go!**
|
|
|
|
| 22 |
|
| 23 |
****
|
| 24 |
|
| 25 |
+
## New Features (2023-06-20)
|
| 26 |
+
- We now support cuda version of both 11.X and 12.X
|
| 27 |
+
- lyraChatGLM has been further optimized, with faster model load speed from few minutes to less than 10s for non-int8 mode, and around 1 min for int8 mode!
|
| 28 |
+
|
| 29 |
## Model Card for lyraChatGLM
|
| 30 |
|
| 31 |
lyraChatGLM is currently the **fastest ChatGLM-6B** available. To the best of our knowledge, it is the **first accelerated version of ChatGLM-6B**.
|