Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Meta-Llama-3.1-8B-Instruct-AQLM-3bit – AI Model by yw223 | AlphaNeural AI
You can deploy this model and start earning money today!
yw223
/
Meta-Llama-3.1-8B-Instruct-AQLM-3bit
like
0
transformers
pytorch
llama
text-generation
aqlm
quantization
weight-only-quantization
conversational
allenai/c4
meta-llama/Llama-3.1-8B-Instruct
quantized
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Meta-Llama-3.1-8B-Instruct-AQLM-3bit
AQLM 3-bit quantized checkpoint derived from
meta-llama/Meta-Llama-3.1-8B-Instruct
.
Quantization
Method: AQLM
Bits: 3
Calibration dataset: C4
Calibration samples: 128
Calibration sequence length: 512
Validation samples: 16
Fine-tuning epochs: 10
