commit wo tf weights

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,218 @@
+---
+language: en
+tags:
+- exbert
+license: apache-2.0
+datasets:
+- bookcorpus
+- wikipedia
+---
+
+# DistilBERT base model (uncased)
+
+This model is a distilled version of the [BERT base model](https://huggingface.co/bert-base-uncased). It was
+introduced in [this paper](https://arxiv.org/abs/1910.01108). The code for the distillation process can be found
+[here](https://github.com/huggingface/transformers/tree/master/examples/distillation). This model is uncased: it does
+not make a difference between english and English.
+
+## Model description
+
+DistilBERT is a transformers model, smaller and faster than BERT, which was pretrained on the same corpus in a
+self-supervised fashion, using the BERT base model as a teacher. This means it was pretrained on the raw texts only,
+with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic
+process to generate inputs and labels from those texts using the BERT base model. More precisely, it was pretrained
+with three objectives:
+
+- Distillation loss: the model was trained to return the same probabilities as the BERT base model.
+- Masked language modeling (MLM): this is part of the original training loss of the BERT base model. When taking a
+  sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the
+  model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that
+  usually see the words one after the other, or from autoregressive models like GPT which internally mask the future
+  tokens. It allows the model to learn a bidirectional representation of the sentence.
+- Cosine embedding loss: the model was also trained to generate hidden states as close as possible as the BERT base
+  model.
+
+This way, the model learns the same inner representation of the English language than its teacher model, while being
+faster for inference or downstream tasks.
+
+## Intended uses & limitations
+
+You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
+be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=distilbert) to look for
+fine-tuned versions on a task that interests you.
+
+Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
+to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
+generation you should look at model like GPT2.
+
+### How to use
+
+You can use this model directly with a pipeline for masked language modeling:
+
+```python
+>>> from transformers import pipeline
+>>> unmasker = pipeline('fill-mask', model='distilbert-base-uncased')
+>>> unmasker("Hello I'm a [MASK] model.")
+
+[{'sequence': "[CLS] hello i'm a role model. [SEP]",
+  'score': 0.05292855575680733,
+  'token': 2535,
+  'token_str': 'role'},
+ {'sequence': "[CLS] hello i'm a fashion model. [SEP]",
+  'score': 0.03968575969338417,
+  'token': 4827,
+  'token_str': 'fashion'},
+ {'sequence': "[CLS] hello i'm a business model. [SEP]",
+  'score': 0.034743521362543106,
+  'token': 2449,
+  'token_str': 'business'},
+ {'sequence': "[CLS] hello i'm a model model. [SEP]",
+  'score': 0.03462274372577667,
+  'token': 2944,
+  'token_str': 'model'},
+ {'sequence': "[CLS] hello i'm a modeling model. [SEP]",
+  'score': 0.018145186826586723,
+  'token': 11643,
+  'token_str': 'modeling'}]
+```
+
+Here is how to use this model to get the features of a given text in PyTorch:
+
+```python
+from transformers import DistilBertTokenizer, DistilBertModel
+tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
+model = DistilBertModel.from_pretrained("distilbert-base-uncased")
+text = "Replace me by any text you'd like."
+encoded_input = tokenizer(text, return_tensors='pt')
+output = model(**encoded_input)
+```
+
+and in TensorFlow:
+
+```python
+from transformers import DistilBertTokenizer, TFDistilBertModel
+tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
+model = TFDistilBertModel.from_pretrained("distilbert-base-uncased")
+text = "Replace me by any text you'd like."
+encoded_input = tokenizer(text, return_tensors='tf')
+output = model(encoded_input)
+```
+
+### Limitations and bias
+
+Even if the training data used for this model could be characterized as fairly neutral, this model can have biased
+predictions. It also inherits some of
+[the bias of its teacher model](https://huggingface.co/bert-base-uncased#limitations-and-bias).
+
+```python
+>>> from transformers import pipeline
+>>> unmasker = pipeline('fill-mask', model='distilbert-base-uncased')
+>>> unmasker("The White man worked as a [MASK].")
+
+[{'sequence': '[CLS] the white man worked as a blacksmith. [SEP]',
+  'score': 0.1235365942120552,
+  'token': 20987,
+  'token_str': 'blacksmith'},
+ {'sequence': '[CLS] the white man worked as a carpenter. [SEP]',
+  'score': 0.10142576694488525,
+  'token': 10533,
+  'token_str': 'carpenter'},
+ {'sequence': '[CLS] the white man worked as a farmer. [SEP]',
+  'score': 0.04985016956925392,
+  'token': 7500,
+  'token_str': 'farmer'},
+ {'sequence': '[CLS] the white man worked as a miner. [SEP]',
+  'score': 0.03932540491223335,
+  'token': 18594,
+  'token_str': 'miner'},
+ {'sequence': '[CLS] the white man worked as a butcher. [SEP]',
+  'score': 0.03351764753460884,
+  'token': 14998,
+  'token_str': 'butcher'}]
+
+>>> unmasker("The Black woman worked as a [MASK].")
+
+[{'sequence': '[CLS] the black woman worked as a waitress. [SEP]',
+  'score': 0.13283951580524445,
+  'token': 13877,
+  'token_str': 'waitress'},
+ {'sequence': '[CLS] the black woman worked as a nurse. [SEP]',
+  'score': 0.12586183845996857,
+  'token': 6821,
+  'token_str': 'nurse'},
+ {'sequence': '[CLS] the black woman worked as a maid. [SEP]',
+  'score': 0.11708822101354599,
+  'token': 10850,
+  'token_str': 'maid'},
+ {'sequence': '[CLS] the black woman worked as a prostitute. [SEP]',
+  'score': 0.11499975621700287,
+  'token': 19215,
+  'token_str': 'prostitute'},
+ {'sequence': '[CLS] the black woman worked as a housekeeper. [SEP]',
+  'score': 0.04722772538661957,
+  'token': 22583,
+  'token_str': 'housekeeper'}]
+```
+
+This bias will also affect all fine-tuned versions of this model.
+
+## Training data
+
+DistilBERT pretrained on the same data as BERT, which is [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset
+consisting of 11,038 unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia)
+(excluding lists, tables and headers).
+
+## Training procedure
+
+### Preprocessing
+
+The texts are lowercased and tokenized using WordPiece and a vocabulary size of 30,000. The inputs of the model are
+then of the form:
+
+```
+[CLS] Sentence A [SEP] Sentence B [SEP]
+```
+
+With probability 0.5, sentence A and sentence B correspond to two consecutive sentences in the original corpus and in
+the other cases, it's another random sentence in the corpus. Note that what is considered a sentence here is a
+consecutive span of text usually longer than a single sentence. The only constrain is that the result with the two
+"sentences" has a combined length of less than 512 tokens.
+
+The details of the masking procedure for each sentence are the following:
+- 15% of the tokens are masked.
+- In 80% of the cases, the masked tokens are replaced by `[MASK]`.
+- In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
+- In the 10% remaining cases, the masked tokens are left as is.
+
+### Pretraining
+
+The model was trained on 8 16 GB V100 for 90 hours. See the
+[training code](https://github.com/huggingface/transformers/tree/master/examples/distillation) for all hyperparameters
+details.
+
+## Evaluation results
+
+When fine-tuned on downstream tasks, this model achieves the following results:
+
+Glue test results:
+
+| Task | MNLI | QQP  | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE  |
+|:----:|:----:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|
+|      | 82.2 | 88.5 | 89.2 | 91.3  | 51.3 | 85.8  | 87.5 | 59.9 |
+
+
+### BibTeX entry and citation info
+
+```bibtex
+@article{Sanh2019DistilBERTAD,
+  title={DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter},
+  author={Victor Sanh and Lysandre Debut and Julien Chaumond and Thomas Wolf},
+  journal={ArXiv},
+  year={2019},
+  volume={abs/1910.01108}
+}
+```
+
+<a href="https://huggingface.co/exbert/?model=distilbert-base-uncased">
+	<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
+</a>

config.json

@@ -0,0 +1,22 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForMaskedLM"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.10.0.dev0",
+  "vocab_size": 30522
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:101fa75462994e55b265fd62b0f44b9bb9f4d3fcb0c9d8986d2542850d0f0688
+size 267945836

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e60d71610916da4787c5513c81bc026d415708528295502fb3e1a6fe1485ea7c
+size 267967963

rust_model.ot

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff3dc0119b9399681cf5661a9e450bb2ed2ecdb88338fb2c9d942c579164cc6
+size 361732396

tokenizer_config.json

@@ -0,0 +1,3 @@
+{
+  "do_lower_case": true
+}