Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
SoraWatermarkRemover
Log In
Sign Up
CXDuncan
/
madlad400-3b-mt-optimized-quantized-onnx
like
4
Translation
Transformers
ONNX
JAX
allenai/MADLAD-400
419 languages
t5
text2text-generation
text-generation-inference
arxiv:
2309.04662
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Train
Deploy
Use this model
8bda807
madlad400-3b-mt-optimized-quantized-onnx
4.96 GB
1 contributor
History:
4 commits
CXDuncan
Update README.md
8bda807
verified
almost 2 years ago
.gitattributes
Safe
1.57 kB
Upload 9 files
almost 2 years ago
README.md
Safe
9.5 kB
Update README.md
almost 2 years ago
config.json
Safe
814 Bytes
Upload 9 files
almost 2 years ago
decoder_model_quantized.onnx
1.87 GB
xet
Upload 9 files
almost 2 years ago
decoder_with_past_model_quantized.onnx
1.73 GB
xet
Upload 9 files
almost 2 years ago
encoder_model_quantized.onnx
1.34 GB
xet
Upload 9 files
almost 2 years ago
ort_config.json
Safe
830 Bytes
Upload 9 files
almost 2 years ago
special_tokens_map.json
414 Bytes
Upload 9 files
almost 2 years ago
spiece.model
4.43 MB
xet
Upload 9 files
almost 2 years ago
tokenizer.json
16.6 MB
xet
Upload 9 files
almost 2 years ago
tokenizer_config.json
830 Bytes
Upload 9 files
almost 2 years ago
