Translation
Transformers
PyTorch
TensorFlow
JAX
Rust
ONNX
Safetensors
t5
text2text-generation
summarization
text-generation-inference
Instructions to use google-t5/t5-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google-t5/t5-small with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("translation", model="google-t5/t5-small")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-small") model = AutoModelForSeq2SeqLM.from_pretrained("google-t5/t5-small", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +0 -25
config.json
CHANGED
|
@@ -1,25 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"T5WithLMHeadModel"
|
| 4 |
-
],
|
| 5 |
-
"d_ff": 2048,
|
| 6 |
-
"d_kv": 64,
|
| 7 |
-
"d_model": 512,
|
| 8 |
-
"dropout_rate": 0.1,
|
| 9 |
-
"finetuning_task": null,
|
| 10 |
-
"initializer_factor": 1.0,
|
| 11 |
-
"is_decoder": false,
|
| 12 |
-
"layer_norm_epsilon": 1e-06,
|
| 13 |
-
"n_positions": 512,
|
| 14 |
-
"num_heads": 8,
|
| 15 |
-
"num_labels": 2,
|
| 16 |
-
"num_layers": 6,
|
| 17 |
-
"output_attentions": false,
|
| 18 |
-
"output_hidden_states": false,
|
| 19 |
-
"output_past": true,
|
| 20 |
-
"pruned_heads": {},
|
| 21 |
-
"relative_attention_num_buckets": 32,
|
| 22 |
-
"torchscript": false,
|
| 23 |
-
"use_bfloat16": false,
|
| 24 |
-
"vocab_size": 32128
|
| 25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|