Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
mobiuslabsgmbh
/
Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bit-metaoffload-HQQ
like
15
Follow
Mobius Labs GmbH
59
Text Generation
Transformers
mixtral
Mixture of Experts
conversational
License:
apache-2.0
Model card
Files
Files and versions
Community
3
Train
Deploy
Use this model
9ed79d7
Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bit-metaoffload-HQQ
/
README.md
Commit History
adding streaming in the example provided
9ed79d7
verified
appoose
commited on
Feb 23, 2024
adding vram usage
48d4273
verified
appoose
commited on
Feb 23, 2024
adding initial metrics
956a729
verified
appoose
commited on
Feb 23, 2024
Update README.md
49119b7
verified
appoose
commited on
Feb 23, 2024
Update README.md
3d7f303
verified
mobicham
commited on
Feb 23, 2024
Update README.md
8c0da45
verified
mobicham
commited on
Feb 23, 2024
initial commit
a671496
verified
mobicham
commited on
Feb 23, 2024