Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
nvidia
/
gpt3-8b-multi-3.5t-base
like
8
Follow
NVIDIA
23.7k
Text Generation
English
Megatron-LM
nvidia
Mamba
Mamba-2
SSM
8B
arxiv:
2406.07887
arxiv:
2405.21060
License:
apache-2.0
Model card
Files
Files and versions
Community
1
51d7f04
gpt3-8b-multi-3.5t-base
/
release
/
mp_rank_00
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
rwaleffe
Update model arguments
51d7f04
11 months ago
model_optim_rng.pt
pickle
Detected Pickle imports (6)
"torch._utils._rebuild_tensor_v2"
,
"torch.bfloat16"
,
"collections.OrderedDict"
,
"torch.BFloat16Storage"
,
"argparse.Namespace"
,
"megatron.core.enums.ModelType"
How to fix it?
17.1 GB
LFS
Update model arguments
11 months ago