Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
opt-6.7b-w8a8-unstructured50 – AI Model by yujiepan | AlphaNeural AI
You can deploy this model and start earning money today!
yujiepan
/
opt-6.7b-w8a8-unstructured50
like
0
transformers
openvino
opt
text-generation
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
yujiepan/opt-6.7b-w8a8-unstructured50
This model is w8a8 quantized & unstructually sparsified by OpenVINO, exported from
facebook/opt-6.7b
.
This model is not tuned for accuracy.
Quantization: 8-bit symmetric for weights & activations
Unstructured sparsity in transformer block linear layers: 50%
Codes for export:
https://gist.github.com/yujiepan-work/1e6dd9f9c2aac0e9ecaf2ed4d82d1158