Adding model

README.md

@@ -0,0 +1,15 @@
+---
+language:
+- is
+license: cc-by-4.0
+datasets:
+- igc
+---
+
+# Icelandic ELECTRA-Small
+This model was pretrained on the [Icelandic Gigaword Corpus](http://igc.arnastofnun.is/), which contains approximately 1.69B tokens, using default settings. The model uses a WordPiece tokenizer with a vocabulary size of 32,105.
+
+# Acknowledgments
+This research was supported with Cloud TPUs from Google's TPU Research Cloud (TRC).
+
+This project was funded by the Language Technology Programme for Icelandic 2019-2023. The programme, which is managed and coordinated by [Almannarómur](https://almannaromur.is/), is funded by the Icelandic Ministry of Education, Science and Culture.

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "ElectraForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "type_vocab_size": 2,
+  "vocab_size": 32105
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2a0a48a7e201a5bf94f41a0ff0e01c962df7a3daed5077f78e2bcaa57944d59
+size 55089961

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, "strip_accents": false, "model_max_length": 128}