Initial commit

README.md

@@ -1,3 +1,15 @@
----
-license: cc-by-4.0
----
+---
+language:
+- is
+license: cc-by-4.0
+datasets:
+- igc
+---
+
+# Icelandic TEAMS-Small
+This model was pre-trained on the 2022 version of the [Icelandic Gigaword Corpus](http://igc.arnastofnun.is/) using the [TensorFlow Model Garden](https://github.com/tensorflow/models). Its pre-training configuration is identical to that of the original [TEAMS-Small model](https://github.com/tensorflow/models/blob/master/official/projects/teams/experiments/small/wiki_books_pretrain.yaml), except for the use of a Unigram tokenizer with a vocabulary size of 64,105.
+
+TEAMS is a variant of the ELECTRA architecture, described in [Training ELECTRA Augmented with Multi-word Selection](https://aclanthology.org/2021.findings-acl.219/). While architecturally equivalent to ELECTRA, TEAMS introduces an additional pre-training objective.
+
+# Acknowledgments
+This research was supported with Cloud TPUs from Google's TPU Research Cloud (TRC).

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "ElectraForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64105
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c29b5380614a4bcae582df3d84a5d38337d69224bd98d0b522b65a677c5cf8
+size 71414748

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82d3c3361fc4db7b4727799293acb097560188a20145e266ec733f98471eb3ae
+size 71458038

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": 512}