Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
Llama-3.1-8B-Instruct-2bit-SqueezeLLM – AI Model by jusjinuk | AlphaNeural AI | AlphaNeural AI
You can deploy this model and start earning money today!
jusjinuk
/
Llama-3.1-8B-Instruct-2bit-SqueezeLLM
like
0
pytorch
llama
2505.07004
meta-llama/Llama-3.1-8B-Instruct
quantized
llama3.1
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Model Card
Base model:
meta-llama/Llama-3.1-8B-Instruct
Quantization method: SqueezeLLM
Target bit-width: 2
Backend kernel: Any-Precision-LLM kernel (
ap-gemv
)
Calibration data: RedPajama (1024 sentences / 4096 tokens)
Calibration objective: Next-token prediction
How to run
Follow the instruction in
https://github.com/snu-mllab/GuidedQuant
.
References
Model Paper
