Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
mobiuslabsgmbh
/
Mixtral-8x7B-Instruct-v0.1-hf-4bit_g64-HQQ
like
9
Follow
Mobius Labs GmbH
55
Text Generation
Transformers
mixtral
Mixture of Experts
conversational
License:
apache-2.0
Model card
Files
Files and versions
Community
4
Train
Deploy
Use this model
055e6de
Mixtral-8x7B-Instruct-v0.1-hf-4bit_g64-HQQ
2 contributors
History:
6 commits
librarian-bot
Librarian Bot: Add moe tag to model
055e6de
11 months ago
.gitattributes
1.52 kB
initial commit
12 months ago
README.md
4.01 kB
Librarian Bot: Add moe tag to model
11 months ago
config.json
774 Bytes
upload model
12 months ago
qmodel.pt
25.9 GB
LFS
upload model
12 months ago
special_tokens_map.json
414 Bytes
upload model
12 months ago
tokenizer.json
1.8 MB
upload model
12 months ago
tokenizer.model
493 kB
LFS
upload model
12 months ago
tokenizer_config.json
1.46 kB
upload model
12 months ago