Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
nvidia
/
mamba2-hybrid-8b-3t-128k
like
42
Follow
NVIDIA
3,379
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
4
New discussion
New pull request
Resources
PR & discussions documentation
Code of Conduct
Hub documentation
All
Discussions
Pull requests
View closed (2)
Convert to HF format
#4 opened 3 months ago by
mrfakename
memba2-hybrid model inference speed vs Transformer-vLLM solutions
#3 opened 4 months ago by
LarryLi