GreenBitAI
/

Mistral-7B-Instruct-v0.2-layer-mix-bpw-2.2

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

GreenBit LLMs

This is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.

Please refer to our Github page for the code to run the model and more information.

Downloads last month: 6

Safetensors

Model size

942M params

Tensor type

I32

·

FP16

·

I16

·

Collection including GreenBitAI/Mistral-7B-Instruct-v0.2-layer-mix-bpw-2.2

GreenBitAI Mistral

GreenBitAI's Mistral family in low-bit format • 9 items • Updated Apr 24