Quants
Collection
Miscellaneous quantifications, mostly GGUF • 18 items • Updated • 1
facebook/wmt21-dense-24-wide-en-x translation model in int8 (4.7gb), cf. the model as safetensor
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("cstr/wmt21ct2_int8", dtype="auto")