MADLAD-400: A Multilingual And Document-Level Large Audited Dataset
Paper • 2309.04662 • Published • 26
MADLAD-400 3B MT — int5 (MLX)
A 5-bit, group-size-64 MLX quantization of
google/madlad400-3b-mt (a T5 encoder–decoder),
for fast on-device translation on Apple Silicon. 400+ languages. Architecture unchanged — this
repo only re-quantizes the original weights.
| Base model | google/madlad400-3b-mt |
| Quantization | 5-bit, group size 64 (the 32×16 relative-attention-bias tables are kept in full precision) |
| Format | MLX safetensors (+ SentencePiece tokenizer) |
| Size | ~2.1 GB |
License & attribution
Apache-2.0, inherited from the base model. All credit for the model goes to Google — see MADLAD-400. This repository only provides an MLX-quantized copy of the released weights.
- Downloads last month
- 34
Model size
0.6B params
Tensor type
F32
·
U32 ·
F16 ·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for huggingfinger0/MADLAD400-3B-MT-int5-MLX
Base model
google/madlad400-3b-mt