Transformers
PyTorch
TensorFlow
JAX
English
t5
text2text-generation
deep-narrow
text-generation-inference
Instructions to use google/t5-efficient-xl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/t5-efficient-xl with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/t5-efficient-xl") model = AutoModelForSeq2SeqLM.from_pretrained("google/t5-efficient-xl", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
e5fb80a
1
Parent(s): eedca21
Update README.md
Browse files
README.md
CHANGED
|
@@ -50,6 +50,7 @@ The *conventional* T5 architectures are summarized in the following table:
|
|
| 50 |
|
| 51 |
with the following definitions:
|
| 52 |
|
|
|
|
| 53 |
| NL | Number of transformer blocks (depth) |
|
| 54 |
| EL | Number of transformer blocks in the encoder (encoder depth) |
|
| 55 |
| DL | Number of transformer blocks in the decoder (decoder depth) |
|
|
|
|
| 50 |
|
| 51 |
with the following definitions:
|
| 52 |
|
| 53 |
+
| ----| ---- |
|
| 54 |
| NL | Number of transformer blocks (depth) |
|
| 55 |
| EL | Number of transformer blocks in the encoder (encoder depth) |
|
| 56 |
| DL | Number of transformer blocks in the decoder (decoder depth) |
|