alphaXiv
/

filter-2b-gptq-int4

compressed-tensors

Model card Files Files and versions

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

alphaXiv/filter-2b-gptq-int4

This is the GPTQ int4 quantized release of alphaXiv/filter-2b.

Quantization

Base model: alphaXiv/filter-2b
Method: GPTQ
Scheme: W4A16
Weight bits: 4
Group size: 128
actorder: weight
lm_head excluded from compression

Files

model.safetensors
config.json
generation_config.json
tokenizer files
recipe.yaml

Notes

The quantization metadata is stored in config.json under quantization_config.

Downloads last month: 59

Safetensors

Model size

2B params

Tensor type

I64

·

I32

·

BF16

·

Inference Providers NEW

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