Instructions to use windowsartes/convbert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use windowsartes/convbert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="windowsartes/convbert")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("windowsartes/convbert") model = AutoModelForMaskedLM.from_pretrained("windowsartes/convbert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from windowsartes/convbert: direct link, hf CLI and curl.
- Browser
- Download file 723 Bytes
-
https://huggingface.co/windowsartes/convbert/resolve/main/config.json
- Command line
-
hf download hf://windowsartes/convbert/config.json
-
curl -L -o config.json https://huggingface.co/windowsartes/convbert/resolve/main/config.json
723 Bytes
| { | |
| "_name_or_path": "/content/drive/MyDrive/model/conv_bert", | |
| "architectures": [ | |
| "ConvBertForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "conv_kernel_size": 9, | |
| "embedding_size": 768, | |
| "eos_token_id": 2, | |
| "head_ratio": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 384, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 26, | |
| "model_type": "convbert", | |
| "num_attention_heads": 12, | |
| "num_groups": 1, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.1", | |
| "type_vocab_size": 2, | |
| "vocab_size": 907 | |
| } | |