Instructions to use kiddothe2b/hierarchical-transformer-base-4096 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kiddothe2b/hierarchical-transformer-base-4096 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="kiddothe2b/hierarchical-transformer-base-4096", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("kiddothe2b/hierarchical-transformer-base-4096", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from kiddothe2b/hierarchical-transformer-base-4096: direct link, hf CLI and curl.
- Browser
- Download file 2.45 kB
-
https://huggingface.co/kiddothe2b/hierarchical-transformer-base-4096/resolve/162074d9d014f1ce6dbcccfe3500c3975a3c44cd/config.json
- Command line
-
hf download hf://kiddothe2b/hierarchical-transformer-base-4096@162074d9d014f1ce6dbcccfe3500c3975a3c44cd/config.json
-
curl -L -o config.json https://huggingface.co/kiddothe2b/hierarchical-transformer-base-4096/resolve/162074d9d014f1ce6dbcccfe3500c3975a3c44cd/config.json
2.45 kB
| { | |
| "_name_or_path": "kiddothe2b/hierarchical-transformer-base-4096", | |
| "architectures": [ | |
| "HATForMaskedLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_hat.HATConfig", | |
| "AutoTokenizer": "tokenization_hat.HATTokenizer", | |
| "AutoModel": "modelling_hat.HATModel", | |
| "AutoModelForMaskedLM": "modelling_hat.HATForMaskedLM", | |
| "AutoModelForMultipleChoice": "modelling_hat.HATForMultipleChoice", | |
| "AutoModelForQuestionAnswering": "modelling_hat.HATForQuestionAnswering", | |
| "AutoModelForSequenceClassification": "modelling_hat.HATForSequenceClassification", | |
| "AutoModelForTokenClassification": "modelling_hat.HATForTokenClassification" | |
| }, | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "encoder_layout": { | |
| "0": { | |
| "document_encoder": false, | |
| "sentence_encoder": true | |
| }, | |
| "1": { | |
| "document_encoder": false, | |
| "sentence_encoder": true | |
| }, | |
| "10": { | |
| "document_encoder": false, | |
| "sentence_encoder": true | |
| }, | |
| "11": { | |
| "document_encoder": true, | |
| "sentence_encoder": true | |
| }, | |
| "2": { | |
| "document_encoder": true, | |
| "sentence_encoder": true | |
| }, | |
| "3": { | |
| "document_encoder": false, | |
| "sentence_encoder": true | |
| }, | |
| "4": { | |
| "document_encoder": false, | |
| "sentence_encoder": true | |
| }, | |
| "5": { | |
| "document_encoder": true, | |
| "sentence_encoder": true | |
| }, | |
| "6": { | |
| "document_encoder": false, | |
| "sentence_encoder": true | |
| }, | |
| "7": { | |
| "document_encoder": false, | |
| "sentence_encoder": true | |
| }, | |
| "8": { | |
| "document_encoder": true, | |
| "sentence_encoder": true | |
| }, | |
| "9": { | |
| "document_encoder": false, | |
| "sentence_encoder": true | |
| } | |
| }, | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 130, | |
| "max_sentence_length": 128, | |
| "max_sentence_size": 128, | |
| "max_sentences": 32, | |
| "model_max_length": 4096, | |
| "model_type": "hierarchical-transformer", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 1, | |
| "parameters": 136350720, | |
| "position_embedding_type": "absolute", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.19.0.dev0", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 50265 | |
| } | |