Duplicate from mercelisw/electra-grc

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,30 @@
+---
+language:
+- grc
+tags:
+- ELECTRA
+- TensorFlow
+---
+
+
+
+An ELECTRA-small model for Ancient Greek, trained on texts from Homer up until the 4th century AD from the literary [GLAUx](https://github.com/alekkeersmaekers/glaux) corpus and the [DukeNLP](https://github.com/alekkeersmaekers/duke-nlp) papyrus corpus.
+
+The model has some design choices made to combat data sparsity:
+* Its input should always be in Unicode NFD (so separate Unicode signs for diacritics).
+* All grave accents should be replaced with acute accents (καί, not καὶ).
+* When a word contains two accents, the second one should be removed (εἶπε μοι, not εἶπέ μοι).
+
+If you use it in conjunction with [glaux-nlp](https://github.com/alekkeersmaekers/glaux-nlp), you can pass the tokenized sentence to normalize_tokens from tokenization.Tokenization, using normalization_rule=greek_glaux, which will do all these normalizations for you. 
+
+## Citation
+
+```bibtex
+@misc{mercelis_electra-grc_2022,
+	title = {electra-grc},
+	url = {https://huggingface.co/mercelisw/electra-grc},
+	abstract = {An ELECTRA-small model for Ancient Greek, trained on texts from Homer up until the 4th century AD.},
+	author = {Mercelis, Wouter and Keersmaekers, Alek},
+	year = {2022},
+}
+```

config.json

@@ -0,0 +1,15 @@
+{
+  "vocab_size": 32000,
+  "embedding_size": 128,
+  "hidden_size": 256,
+  "num_hidden_layers": 12,
+  "num_attention_heads": 4,
+  "intermediate_size": 1024,
+  "generator_size": "0.25",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.1,
+  "max_position_embeddings": 512,
+  "type_vocab_size": 2,
+  "initializer_range": 0.02
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606da6bfd2f2c55deb9112e74d43afdb842e8d00bd2e57e3aadaae75dac6a26b
+size 57983495

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "texts/models/electra-grc-2", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}