Edit model card

Gemma-2-2B-it-4Bit-GPTQ

Quantization

This model was quantized with the Auto-GPTQ library and dataset containing english and russian wikipedia articles. It has lower perplexity on russian data then other GPTQ models.

Safetensors

Model size

861M params

Tensor type

I32

FP16

Inference Examples

Inference API (serverless) has been turned off for this model.

Base model

Finetuned

Quantized

(94)

this model