Instructions to use bubai567/nifty_bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bubai567/nifty_bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="bubai567/nifty_bert")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("bubai567/nifty_bert") model = AutoModelForSequenceClassification.from_pretrained("bubai567/nifty_bert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from bubai567/nifty_bert: direct link, hf CLI and curl.
- Browser
- Download file 828 Bytes
-
https://huggingface.co/bubai567/nifty_bert/resolve/main/config.json
- Command line
-
hf download hf://bubai567/nifty_bert/config.json
-
curl -L -o config.json https://huggingface.co/bubai567/nifty_bert/resolve/main/config.json
828 Bytes
| { | |
| "_name_or_path": "nlpaueb/legal-bert-small-uncased", | |
| "architectures": [ | |
| "BertForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_ids": 0, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 512, | |
| "id2label": { | |
| "0": "SELL", | |
| "1": "HOLD", | |
| "2": "BUY" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "label2id": { | |
| "BUY": 2, | |
| "HOLD": 1, | |
| "SELL": 0 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 6, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "transformers_version": "4.33.2", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 30522 | |
| } | |