nvidia
/

Llama-3.1-8B-Medusa-FP8

Model card Files Files and versions

Llama-3.1-8B-Medusa-FP8

12.8 GB

Ctrl+K

Ctrl+K

2 contributors

History: 9 commits

zhiyucheng's picture

fix tokenizer

e3d0d5e verified about 1 year ago

.gitattributes

1.52 kB
update model card and include license file almost 2 years ago
LICENSE.pdf

152 kB
update model card and include license file almost 2 years ago
README.md

8.39 kB
update readme almost 2 years ago
config.json

982 Bytes
update model card and include license file almost 2 years ago
generation_config.json

184 Bytes
update model card and include license file almost 2 years ago
hf_quant_config.json

256 Bytes
update model card and include license file almost 2 years ago
model-00001-of-00003.safetensors

4.98 GB
xet

update model card and include license file almost 2 years ago
model-00002-of-00003.safetensors

4.1 GB
xet

update model card and include license file almost 2 years ago
model-00003-of-00003.safetensors

3.73 GB
xet

update model card and include license file almost 2 years ago
model.safetensors.index.json

69.7 kB
update model card and include license file almost 2 years ago
special_tokens_map.json

439 Bytes
update model card and include license file almost 2 years ago
tokenizer.json

9.09 MB
fix tokenizer about 1 year ago
tokenizer_config.json

51.1 kB
update model card and include license file almost 2 years ago