Instructions to use jdjsjsj28828/tcprobe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jdjsjsj28828/tcprobe with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="jdjsjsj28828/tcprobe")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("jdjsjsj28828/tcprobe") model = AutoModelForTokenClassification.from_pretrained("jdjsjsj28828/tcprobe", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from jdjsjsj28828/tcprobe: direct link, hf CLI and curl.
- Browser
- Download file 748 Bytes
-
https://huggingface.co/jdjsjsj28828/tcprobe/resolve/main/config.json
- Command line
-
hf download hf://jdjsjsj28828/tcprobe/config.json
-
curl -L -o config.json https://huggingface.co/jdjsjsj28828/tcprobe/resolve/main/config.json
748 Bytes
| {"_name_or_path": "temp/dummy/bert/BertForTokenClassification", "architectures": ["BertForTokenClassification"], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 4, "num_hidden_layers": 5, "pad_token_id": 0, "position_embedding_type": "absolute", "torch_dtype": "float32", "transformers_version": "4.25.0.dev0", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1124, "id2label": {"0": "<img src=x onerror=window.__tc=1>", "1": "B-PER"}, "label2id": {"<img src=x onerror=window.__tc=1>": 0, "B-PER": 1}} |