Transformers
PyTorch
TensorFlow
JAX
English
t5
text2text-generation
deep-narrow
text-generation-inference
Instructions to use google/t5-efficient-base-nh24 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/t5-efficient-base-nh24 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/t5-efficient-base-nh24") model = AutoModelForSeq2SeqLM.from_pretrained("google/t5-efficient-base-nh24", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from google/t5-efficient-base-nh24: direct link, hf CLI and curl.
- Browser
- Download file 636 Bytes
-
https://huggingface.co/google/t5-efficient-base-nh24/resolve/main/config.json
- Command line
-
hf download hf://google/t5-efficient-base-nh24/config.json
-
curl -L -o config.json https://huggingface.co/google/t5-efficient-base-nh24/resolve/main/config.json
636 Bytes
| { | |
| "_name_or_path": "t5-efficient-base-nh24", | |
| "architectures": [ | |
| "T5ForConditionalGeneration" | |
| ], | |
| "d_ff": 3072, | |
| "d_kv": 64, | |
| "d_model": 768, | |
| "decoder_start_token_id": 0, | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "relu", | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "t5", | |
| "n_positions": 512, | |
| "num_decoder_layers": 12, | |
| "num_heads": 24, | |
| "num_layers": 12, | |
| "pad_token_id": 0, | |
| "relative_attention_num_buckets": 32, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.17.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 32128 | |
| } | |