kiri-ai
/

gpt2-large-quantized

Text Generation Transformers English gpt2 Inference Endpoints text-generation-inference

Model card Files Files and versions Community

Edit model card

Pytorch int8 quantized version of gpt2-large

Usage

Download the .bin file locally. Load with:

Rest of the usage according to original instructions.

import torch

model = torch.load("path/to/pytorch_model_quantized.bin")

Downloads last month: 16