Update README.md

README.md

@@ -1,3 +1,159 @@
 ---
 license: cc-by-4.0
+language:
+- he
+inference: false
 ---
+# DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew
+
+State-of-the-art language model for Hebrew, released [here](https://arxiv.org/abs/2308.16687).
+
+This is the fine-tuned model for the syntax dependency tree parsing task.  
+
+For the bert-base models for other tasks, see [here](https://huggingface.co/collections/dicta-il/dictabert-6588e7cc08f83845fc42a18b).
+
+Sample usage:
+
+```python
+from transformers import AutoModel, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained('dicta-il/dictabert-syntax')
+model = AutoModel.from_pretrained('dicta-il/dictabert-syntax', trust_remote_code=True)
+
+model.eval()
+
+sentence = 'בשנת 1948 השלים אפרים קישון את לימודיו בפיסול מתכת ובתולדות האמנות והחל לפרסם מאמרים הומוריסטיים'
+print(model.predict([sentence], tokenizer))
+```
+
+Output:
+```json
+[
+  {
+    "tree": [
+      {
+        "word": "בשנת",
+        "dep_head_idx": 2,
+        "dep_head": "השלים",
+        "dep_func": "obl"
+      },
+      {
+        "word": "1948",
+        "dep_head_idx": 0,
+        "dep_head": "בשנת",
+        "dep_func": "compound"
+      },
+      {
+        "word": "השלים",
+        "dep_head_idx": -1,
+        "dep_head": "root",
+        "dep_func": "root"
+      },
+      {
+        "word": "אפרים",
+        "dep_head_idx": 2,
+        "dep_head": "השלים",
+        "dep_func": "nsubj"
+      },
+      {
+        "word": "קישון",
+        "dep_head_idx": 3,
+        "dep_head": "אפרים",
+        "dep_func": "flat"
+      },
+      {
+        "word": "את",
+        "dep_head_idx": 6,
+        "dep_head": "לימודיו",
+        "dep_func": "case"
+      },
+      {
+        "word": "לימודיו",
+        "dep_head_idx": 2,
+        "dep_head": "השלים",
+        "dep_func": "obj"
+      },
+      {
+        "word": "בפיסול",
+        "dep_head_idx": 6,
+        "dep_head": "לימודיו",
+        "dep_func": "nmod"
+      },
+      {
+        "word": "מתכת",
+        "dep_head_idx": 7,
+        "dep_head": "בפיסול",
+        "dep_func": "compound"
+      },
+      {
+        "word": "ובתולדות",
+        "dep_head_idx": 7,
+        "dep_head": "בפיסול",
+        "dep_func": "conj"
+      },
+      {
+        "word": "האמנות",
+        "dep_head_idx": 9,
+        "dep_head": "ובתו",
+        "dep_func": "compound"
+      },
+      {
+        "word": "והחל",
+        "dep_head_idx": 2,
+        "dep_head": "השלים",
+        "dep_func": "conj"
+      },
+      {
+        "word": "לפרסם",
+        "dep_head_idx": 11,
+        "dep_head": "והחל",
+        "dep_func": "xcomp"
+      },
+      {
+        "word": "מאמרים",
+        "dep_head_idx": 12,
+        "dep_head": "לפרסם",
+        "dep_func": "obj"
+      },
+      {
+        "word": "הומוריסטיים",
+        "dep_head_idx": 13,
+        "dep_head": "מאמרים",
+        "dep_func": "amod"
+      }
+    ],
+    "root_idx": 2
+  }
+]
+```
+
+
+## Citation
+
+If you use DictaBERT in your research, please cite ```DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew```
+
+**BibTeX:**
+
+```bibtex
+@misc{shmidman2023dictabert,
+      title={DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew}, 
+      author={Shaltiel Shmidman and Avi Shmidman and Moshe Koppel},
+      year={2023},
+      eprint={2308.16687},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
+
+## License
+
+Shield: [![CC BY 4.0][cc-by-shield]][cc-by]
+
+This work is licensed under a
+[Creative Commons Attribution 4.0 International License][cc-by].
+
+[![CC BY 4.0][cc-by-image]][cc-by]
+
+[cc-by]: http://creativecommons.org/licenses/by/4.0/
+[cc-by-image]: https://i.creativecommons.org/l/by/4.0/88x31.png
+[cc-by-shield]: https://img.shields.io/badge/License-CC%20BY%204.0-lightgrey.svg