jjeccles
/

autoround-quantized-4bit

4-bit precision

Model card Files Files and versions Community

AutoRound 4-bit Quantized Model

This is a 4-bit quantized version of jjeccles/combined-filtercompressedthink-documentnohours-merged created using AutoRound.

Quantization Parameters

Bits: 4
Group Size: 128
Symmetric: False
Samples: 512
Iterations: 1000

Downloads last month: 2

Safetensors

Model size

683M params

Tensor type

I32

·

BF16

·

FP16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support