Transformers
PyTorch
TensorFlow
JAX
English
t5
text2text-generation
deep-narrow
text-generation-inference
Instructions to use google/t5-efficient-large-nl36 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/t5-efficient-large-nl36 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/t5-efficient-large-nl36") model = AutoModelForSeq2SeqLM.from_pretrained("google/t5-efficient-large-nl36") - Notebooks
- Google Colab
- Kaggle
Fix grammar
#1
by furkan1618 - opened
README.md
CHANGED
|
@@ -71,7 +71,7 @@ whereas the following abbreviations are used:
|
|
| 71 |
| sh | Signifies that attention heads are shared |
|
| 72 |
| skv | Signifies that key-values projection matrices are tied |
|
| 73 |
|
| 74 |
-
If a model checkpoint has no specific
|
| 75 |
|
| 76 |
## Pre-Training
|
| 77 |
|
|
|
|
| 71 |
| sh | Signifies that attention heads are shared |
|
| 72 |
| skv | Signifies that key-values projection matrices are tied |
|
| 73 |
|
| 74 |
+
If a model checkpoint has no specific *el* or *dl*, then both of the numbers of encoder and decoder layers correspond to *nl*.
|
| 75 |
|
| 76 |
## Pre-Training
|
| 77 |
|