copy of original repo

.gitattributes

@@ -1,27 +1,9 @@
-*.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
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 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
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,22 @@
+TinyBERT: Distilling BERT for Natural Language Understanding
+======== 
+
+**This model is a copy of [this model repository](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) from Huawei Noah at the specific commit `34707a33cd59a94ecde241ac209bf35103691b43`.**
+
+TinyBERT is 7.5x smaller and 9.4x faster on inference than BERT-base and achieves competitive performances in the tasks of natural language understanding. It performs a novel transformer distillation at both the pre-training and task-specific learning stages. In general distillation, we use the original BERT-base without fine-tuning as the teacher and a large-scale text corpus as the learning data. By performing the Transformer distillation on the text from general domain, we obtain a general TinyBERT which provides a good initialization for the task-specific distillation. We here provide the general TinyBERT for your tasks at hand.
+
+For more details about the techniques of TinyBERT, refer to our paper:
+[TinyBERT: Distilling BERT for Natural Language Understanding](https://arxiv.org/abs/1909.10351)
+
+
+Citation
+========
+If you find TinyBERT useful in your research, please cite the following paper:
+```
+@article{jiao2019tinybert,
+  title={Tinybert: Distilling bert for natural language understanding},
+  author={Jiao, Xiaoqi and Yin, Yichun and Shang, Lifeng and Jiang, Xin and Chen, Xiao and Li, Linlin and Wang, Fang and Liu, Qun},
+  journal={arXiv preprint arXiv:1909.10351},
+  year={2019}
+}
+```

config.json

@@ -0,0 +1,18 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "cell": {},
+  "model_type": "bert",
+  "emb_size": 312,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "initializer_range": 0.02,
+  "intermediate_size": 1200,
+  "max_position_embeddings": 512,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pre_trained": "",
+  "structure": [],
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:031d75f61b5d4079f0d9be329f768d63ca4d4bc6600b9c6298fdaacd755da699
+size 57403595

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84ac219f2fdab6e7f54fc6db4d7a9493708990b006d58f50cc1dceeef2a12f8a
+size 62747391