Token Classification
Transformers
Safetensors
Ancient Greek (to 1453)
char_bert_joint
ancient-greek
classical-philology
character-level
part-of-speech-tagging
lemmatization
dependency-parsing
custom_code
Instructions to use Ericu950/CharDiff-grc-tagger-parser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ericu950/CharDiff-grc-tagger-parser with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Ericu950/CharDiff-grc-tagger-parser", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Ericu950/CharDiff-grc-tagger-parser", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "n_alpha": 24, | |
| "mask_id": 24, | |
| "blank_id": 25, | |
| "pad_id": 26, | |
| "n_char_ids": 27, | |
| "n_boundary": 4, | |
| "n_dia": 49, | |
| "n_punct": 7, | |
| "d_model": 1024, | |
| "n_heads": 16, | |
| "depth": 32, | |
| "char_window": 256, | |
| "attn_impl": "sdpa", | |
| "qk_norm": true, | |
| "use_cap": true, | |
| "pool": "mean", | |
| "head_dropout": 0.33, | |
| "scalar_mix": true, | |
| "xpos_len": 9, | |
| "n_xpos_classes": [ | |
| 14, | |
| 4, | |
| 4, | |
| 8, | |
| 8, | |
| 5, | |
| 5, | |
| 6, | |
| 3 | |
| ], | |
| "n_script": 18485, | |
| "n_upos": 13, | |
| "use_flat": true, | |
| "n_flat_tags": 1249, | |
| "d_arc": 500, | |
| "d_rel": 150, | |
| "n_labels": 24, | |
| "parse_dropout": 0.33, | |
| "max_chars": 2048, | |
| "max_words": 384, | |
| "model_type": "char_bert_joint", | |
| "auto_map": { | |
| "AutoConfig": "configuration_char_bert_joint.CharBertJointConfig", | |
| "AutoModel": "modeling_char_bert_joint.CharBertForTaggingAndParsing" | |
| } | |
| } |