TMElyralab
/

lyraLLaMA

Model card Files Files and versions

lyraLLaMA / lyra_llama

16.2 kB

Ctrl+K

Ctrl+K

4 contributors

History: 2 commits

carsonhxsu

[NewFeature] Support inference of LLaMA (7B/13B) using int8 quantization

70750a1 almost 3 years ago

__init__.py

33 Bytes
commit message about 3 years ago
config.py

979 Bytes
commit message about 3 years ago
lyra_llama.py

8.37 kB
[NewFeature] Support inference of LLaMA (7B/13B) using int8 quantization almost 3 years ago
model.py

6.85 kB
[NewFeature] Support inference of LLaMA (7B/13B) using int8 quantization almost 3 years ago