Instructions to use Eviation/DistillT5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Eviation/DistillT5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Eviation/DistillT5")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Eviation/DistillT5", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Unwrapped model: renamed tensors from
encoder.encoder.[...]toencoder.[...]to align with T5 XXL.
Available models:
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| DistillT5-F32.safetensors | F32 | 518MB | - |
| DistillT5-BF16.safetensors | BF16 | 259MB | - |
| DistillT5-F15.safetensors | F16 | 259MB | - |
| DistillT5-FP8.safetensors | FP8 (F8_E4M3) | 130MB | - |
Model tree for Eviation/DistillT5
Base model
LifuWang/DistillT5