Add GreTa files

README.md

@@ -0,0 +1,50 @@
+---
+language: grc
+license: apache-2.0
+inference: false
+---
+# GrεTa
+
+The paper [Exploring Language Models for Classical Philology](https://todo.com) is the first effort to systematically provide state-of-the-art language models for Classical Philology. GrεTa is a T5-base sized, monolingual, encoder-decoder variant.  
+
+This model was trained in two stages. Initially, it was pre-trained on a recently acquired corpus that leverages OCR scans obtained from the [Internet Archive](https://archive.org/).  Subsequently, the model was further trained using data from the [Open Greek & Latin Project](https://opengreekandlatin.org/), the CLARIN corpus [Greek Medieval Texts](https://inventory.clarin.gr/corpus/890), and the [Patrologia Graeca](https://patristica.net/graeca/).
+
+
+Further information can be found in our paper or in our [GitHub repository](https://github.com/Heidelberg-NLP/ancient-language-models).
+
+## Usage
+```python
+from transformers import AutoTokenizer, AutoModelForConditionalGeneration
+
+tokenizer = AutoTokenizer.from_pretrained('bowphs/GreTa')
+model = AutoModelForConditionalGeneration.from_pretrained('bowphs/GreTa')
+```
+Please check out the awesome Hugging Face tutorials on how to fine-tune our models.
+
+## Evaluation Results
+When fine-tuned on data from [Universal Dependencies 2.10](https://universaldependencies.org/), GrεTa achieves the following results on the Ancient Greek Perseus dataset:
+
+| Task | XPoS | UPoS  | UAS | LAS | Lemma |
+|:--:|:--:|:--:|:--:|:--:|:--:|
+|      |94.44|89.03|87.32|83.06|91.14|
+
+Please note that the PoS tagging and dependency parsing results are obtained using _only_ the encoder component of the model.
+
+## Contact
+If you have any questions or problems, feel free to [reach out](mailto:riemenschneider@cl.uni-heidelberg.de).
+
+## Citation
+```bibtex
+@incollection{riemenschneiderfrank:2023,
+    address = "Toronto, Canada",
+    author = "Riemenschneider, Frederick and Frank, Anette",
+    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL’23)",
+    note = "to appear",
+    pubType = "incollection",
+    publisher = "Association for Computational Linguistics",
+    title = "Exploring Large Language Models for Classical Philology",
+    url = "https://arxiv.org/abs/2305.13698",
+    year = "2023",
+    key = "riemenschneiderfrank:2023"
+}
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "bowphs/GreTa",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0",
+  "use_cache": true,
+  "vocab_size": 32103
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83b68b042e448cdb0e6282548340bf4293934e3ccb5132a0083d94396809cdc
+size 990170015

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd31d8bbc7898741181c94e476f3a6caba3f13835a5e4fc20ac030190affada
+size 990280781

special_tokens_map.json

@@ -0,0 +1 @@
+{}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4104aa76a73252cf60297b2d9430e0ca5bddbfc06df8b726822cd5778bb8a4
+size 990731600

tokenizer_config.json

@@ -0,0 +1 @@
+{"special_tokens_map_file": null, "name_or_path": "data/t5-base-grc-clean", "tokenizer_class": "PreTrainedTokenizerFast"}