falcon-40b-instruct quantized with GPTQ using the script in https://github.com/huggingface/text-generation-inference/pull/438

  • group size: 128
  • act order: true
  • nsamples: 128
  • dataset: wikitext2
Downloads last month
12
Safetensors
Model size
6.53B params
Tensor type
I64
I32
FP16
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support