Upload 5 files

README.md

@@ -1,3 +1,35 @@
----
-license: mit
----
+This is the ELECTRA-Tiny language model that is effective for discriminative tasks with fewer than 6 million parameters. The embeddings were enriched using multimodal embeddings from a multiplex network. It was trained on the BabyLM 100M dataset. 
+
+### Citation
+
+@inproceedings{fields-etal-2023-tiny,
+    title = "Tiny Language Models Enriched with Multimodal Knowledge from Multiplex Networks",
+    author = "Fields, Clayton  and
+      Natouf, Osama  and
+      McMains, Andrew  and
+      Henry, Catherine  and
+      Kennington, Casey",
+    editor = "Warstadt, Alex  and
+      Mueller, Aaron  and
+      Choshen, Leshem  and
+      Wilcox, Ethan  and
+      Zhuang, Chengxu  and
+      Ciro, Juan  and
+      Mosquera, Rafael  and
+      Paranjabe, Bhargavi  and
+      Williams, Adina  and
+      Linzen, Tal  and
+      Cotterell, Ryan",
+    booktitle = "Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning",
+    month = dec,
+    year = "2023",
+    address = "Singapore",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2023.conll-babylm.3/",
+    doi = "10.18653/v1/2023.conll-babylm.3",
+    pages = "47--57"
+}
+}
+
+### Acknowledgements
+This material is based upon work supported by the National Science Foundation under Grant No. 2140642.

config.json

@@ -0,0 +1,26 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 196,
+  "initializer_range": 0.02,
+  "intermediate_size": 128,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 128,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "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": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2864905003a3efd2e62b571dedf74156651bd21fec3b15bbea8fc99f36dbe48f
+size 30953767

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-small-discriminator", "tokenizer_class": "ElectraTokenizer"}