Hugging Face's logo

TMElyralab
/
lyraXVERSE

English
LLM
XVERSE-13B-Chat
Model card Files Community
1
carsonhxsu commited on
Commit
4d53fc2
·
1 Parent(s): 19ac28c

update README

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -12,7 +12,7 @@ lyraXVERSE is currently the **fastest XVERSE-13b** available. The inferen
12
  Among its main features are:
13
  - device: Nvidia GPU with Amperer architecture or Volta architecture (A100 or higher, V100).
14
  - batch_size: compiled with dynamic batch size, maximum depends on device. 
15
- - MEMOPT mode: significantly optimized memory usage and increased speed
16
 
17
  We use the XVERSE-13B-Chat model for measurement, but this optimized inference is also applicable to XVERSE-13B model.
18
 
 
12
  Among its main features are:
13
  - device: Nvidia GPU with Amperer architecture or Volta architecture (A100 or higher, V100).
14
  - batch_size: compiled with dynamic batch size, maximum depends on device. 
15
+ - MEMOPT mode: significantly optimized VRAM usage and increased speed
16
 
17
  We use the XVERSE-13B-Chat model for measurement, but this optimized inference is also applicable to XVERSE-13B model.
18