first commit

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* 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
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model_patched.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,62 @@
 ---
-license: afl-3.0
+language: 
+  - en
+
+license:
+- mit  
+  
+tags:
+- BERT
+- MNLI
+- NLI
+- transformer
+- pre-training
+
 ---
+
+The following model is a Pytorch pre-trained model obtained from converting Tensorflow checkpoint found in the [official Google BERT repository](https://github.com/google-research/bert). 
+
+This is one of the smaller pre-trained BERT variants, together with [bert-mini](https://huggingface.co/prajjwal1/bert-mini) [bert-small](https://huggingface.co/prajjwal1/bert-small) and [bert-medium](https://huggingface.co/prajjwal1/bert-medium). They were introduced in the study `Well-Read Students Learn Better: On the Importance of Pre-training Compact Models` ([arxiv](https://arxiv.org/abs/1908.08962)), and ported to HF for the study `Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics` ([arXiv](https://arxiv.org/abs/2110.01518)). These models are supposed to be trained on a downstream task.
+
+If you use the model, please consider citing both the papers:
+```
+@misc{bhargava2021generalization,
+      title={Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics}, 
+      author={Prajjwal Bhargava and Aleksandr Drozd and Anna Rogers},
+      year={2021},
+      eprint={2110.01518},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+
+@article{DBLP:journals/corr/abs-1908-08962,
+  author    = {Iulia Turc and
+               Ming{-}Wei Chang and
+               Kenton Lee and
+               Kristina Toutanova},
+  title     = {Well-Read Students Learn Better: The Impact of Student Initialization
+               on Knowledge Distillation},
+  journal   = {CoRR},
+  volume    = {abs/1908.08962},
+  year      = {2019},
+  url       = {http://arxiv.org/abs/1908.08962},
+  eprinttype = {arXiv},
+  eprint    = {1908.08962},
+  timestamp = {Thu, 29 Aug 2019 16:32:34 +0200},
+  biburl    = {https://dblp.org/rec/journals/corr/abs-1908-08962.bib},
+  bibsource = {dblp computer science bibliography, https://dblp.org}
+}
+
+```
+Config of this model:
+- `prajjwal1/bert-tiny` (L=2, H=128) [Model Link](https://huggingface.co/prajjwal1/bert-tiny)
+
+
+Other models to check out:
+- `prajjwal1/bert-mini` (L=4, H=256) [Model Link](https://huggingface.co/prajjwal1/bert-mini)
+- `prajjwal1/bert-small` (L=4, H=512) [Model Link](https://huggingface.co/prajjwal1/bert-small)
+- `prajjwal1/bert-medium` (L=8, H=512) [Model Link](https://huggingface.co/prajjwal1/bert-medium)
+
+Original Implementation and more info can be found in [this Github repository](https://github.com/prajjwal1/generalize_lm_nli).
+
+Twitter: [@prajjwal_1](https://twitter.com/prajjwal_1)

config.json

@@ -0,0 +1 @@
+{"hidden_size": 128, "hidden_act": "gelu", "initializer_range": 0.02, "vocab_size": 30522, "hidden_dropout_prob": 0.1, "num_attention_heads": 2, "type_vocab_size": 2, "max_position_embeddings": 512, "num_hidden_layers": 2, "intermediate_size": 512, "attention_probs_dropout_prob": 0.1}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab2c2bddcfb48ea430ef63fd76d46d67d704487844d967256a50dd7d7fd0a66
+size 17756393

pytorch_model_patched.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:badecf4865f509ae458b1f3ce2c78dbb9dc4f994f7b51c79ff985f2f02dd7727
+size 16429735