Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
aurelian-v0.5-70b-rope8-32K-6bpw_h8_exl2 – AI Model by grimulkan | AlphaNeural AI
You can deploy this model and start earning money today!
grimulkan
/
aurelian-v0.5-70b-rope8-32K-6bpw_h8_exl2
like
0
transformers
safetensors
llama
text-generation
unknown
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
This is a 6-bit EXL2 quantization of
Aurelian v0.5 70B 32K
, an interim checkpoint before v1.0. See that page for more details.
This quantization fits in 48GB+24GB (36/24 split) or 3x24GB (16/17/20 split) using Exllamav2 @ 32k context.
