Skip to content

GitLab

"sgl-router/src/tool_parser/parsers/passthrough.rs" did not exist on "4c9bcb9d5679aa90fc0813861c41bf2a76975f58"
Unverified Commit 3552d0e0 authored by Julien Chaumond's avatar Julien Chaumond Committed by GitHub
Browse files

[model_cards] Migrate cards from this repo to model repos on huggingface.co (#9013) 



* rm all model cards

* Update the .rst

@sgugger it is still not super crystal clear/streamlined so let me know if any ideas to make it simpler

* Add a rootlevel README.md with simple instructions/context

* Update docs/source/model_sharing.rst
Co-authored-by: default avatarSylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Apply suggestions from code review
Co-authored-by: default avatarSylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>

* make style

* rm all model cards
Co-authored-by: default avatarSylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
parent 29e45979
Show whitespace changes
Inline Side-by-side
Showing with 0 additions and 1318 deletions
model_cards/dbmdz/electra-base-turkish-cased-discriminator/README.md deleted 100644 → 0
View file @ 29e45979
---
language: tr
license: mit
---
# 🤗 + 📚 dbmdz Turkish ELECTRA model
In this repository the MDZ Digital Library team (dbmdz) at the Bavarian State
Library open sources a cased ELECTRA base model for Turkish 🎉
# Turkish ELECTRA model
We release a base ELEC**TR**A model for Turkish, that was trained on the same data as *BERTurk*.
> ELECTRA is a new method for self-supervised language representation learning. It can be used to
> pre-train transformer networks using relatively little compute. ELECTRA models are trained to
> distinguish "real" input tokens vs "fake" input tokens generated by another neural network, similar to
> the discriminator of a GAN.
More details about ELECTRA can be found in the [ICLR paper](https://openreview.net/forum?id=r1xMH1BtvB)
or in the [official ELECTRA repository](https://github.com/google-research/electra) on GitHub.
## Stats
The current version of the model is trained on a filtered and sentence
segmented version of the Turkish [OSCAR corpus](https://traces1.inria.fr/oscar/),
a recent Wikipedia dump, various [OPUS corpora](http://opus.nlpl.eu/) and a
special corpus provided by [Kemal Oflazer](http://www.andrew.cmu.edu/user/ko/).
The final training corpus has a size of 35GB and 44,04,976,662 tokens.
Thanks to Google's TensorFlow Research Cloud (TFRC) we could train a cased model
on a TPU v3-8 for 1M steps.
## Model weights
[Transformers](https://github.com/huggingface/transformers)
compatible weights for both PyTorch and TensorFlow are available.
| Model | Downloads
| ------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------
| `dbmdz/electra-base-turkish-cased-discriminator` | [`config.json`](https://cdn.huggingface.co/dbmdz/electra-base-turkish-cased-discriminator/config.json) • [`pytorch_model.bin`](https://cdn.huggingface.co/dbmdz/electra-base-turkish-cased-discriminator/pytorch_model.bin) • [`vocab.txt`](https://cdn.huggingface.co/dbmdz/electra-base-turkish-cased-discriminator/vocab.txt)
## Usage
With Transformers >= 2.8 our ELECTRA base cased model can be loaded like:
```python
from transformers import AutoModelWithLMHead, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("dbmdz/electra-base-turkish-cased-discriminator")
model = AutoModelWithLMHead.from_pretrained("dbmdz/electra-base-turkish-cased-discriminator")
```
## Results
For results on PoS tagging or NER tasks, please refer to
[this repository](https://github.com/stefan-it/turkish-bert/electra).
# Huggingface model hub
All models are available on the [Huggingface model hub](https://huggingface.co/dbmdz).
# Contact (Bugs, Feedback, Contribution and more)
For questions about our ELECTRA models just open an issue
[here](https://github.com/dbmdz/berts/issues/new) 🤗
# Acknowledgments
Thanks to [Kemal Oflazer](http://www.andrew.cmu.edu/user/ko/) for providing us
additional large corpora for Turkish. Many thanks to Reyyan Yeniterzi for providing
us the Turkish NER dataset for evaluation.
Research supported with Cloud TPUs from Google's TensorFlow Research Cloud (TFRC).
Thanks for providing access to the TFRC ❤️
Thanks to the generous support from the [Hugging Face](https://huggingface.co/) team,
it is possible to download both cased and uncased models from their S3 storage 🤗
model_cards/dbmdz/electra-small-turkish-cased-discriminator/README.md deleted 100644 → 0
View file @ 29e45979
---
language: tr
license: mit
---
# 🤗 + 📚 dbmdz Turkish ELECTRA model
In this repository the MDZ Digital Library team (dbmdz) at the Bavarian State
Library open sources a cased ELECTRA small model for Turkish 🎉
# Turkish ELECTRA model
We release a small ELEC**TR**A model for Turkish, that was trained on the same data as *BERTurk*.
> ELECTRA is a new method for self-supervised language representation learning. It can be used to
> pre-train transformer networks using relatively little compute. ELECTRA models are trained to
> distinguish "real" input tokens vs "fake" input tokens generated by another neural network, similar to
> the discriminator of a GAN.
More details about ELECTRA can be found in the [ICLR paper](https://openreview.net/forum?id=r1xMH1BtvB)
or in the [official ELECTRA repository](https://github.com/google-research/electra) on GitHub.
## Stats
The current version of the model is trained on a filtered and sentence
segmented version of the Turkish [OSCAR corpus](https://traces1.inria.fr/oscar/),
a recent Wikipedia dump, various [OPUS corpora](http://opus.nlpl.eu/) and a
special corpus provided by [Kemal Oflazer](http://www.andrew.cmu.edu/user/ko/).
The final training corpus has a size of 35GB and 44,04,976,662 tokens.
Thanks to Google's TensorFlow Research Cloud (TFRC) we could train a cased model
on a TPU v3-8 for 1M steps.
## Model weights
[Transformers](https://github.com/huggingface/transformers)
compatible weights for both PyTorch and TensorFlow are available.
| Model | Downloads
| ------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------
| `dbmdz/electra-small-turkish-cased-discriminator` | [`config.json`](https://cdn.huggingface.co/dbmdz/electra-small-turkish-cased-discriminator/config.json) • [`pytorch_model.bin`](https://cdn.huggingface.co/dbmdz/electra-small-turkish-cased-discriminator/pytorch_model.bin) • [`vocab.txt`](https://cdn.huggingface.co/dbmdz/electra-small-turkish-cased-discriminator/vocab.txt)
## Usage
With Transformers >= 2.8 our ELECTRA small cased model can be loaded like:
```python
from transformers import AutoModelWithLMHead, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("dbmdz/electra-small-turkish-cased-discriminator")
model = AutoModelWithLMHead.from_pretrained("dbmdz/electra-small-turkish-cased-discriminator")
```
## Results
For results on PoS tagging or NER tasks, please refer to
[this repository](https://github.com/stefan-it/turkish-bert/electra).
# Huggingface model hub
All models are available on the [Huggingface model hub](https://huggingface.co/dbmdz).
# Contact (Bugs, Feedback, Contribution and more)
For questions about our ELECTRA models just open an issue
[here](https://github.com/dbmdz/berts/issues/new) 🤗
# Acknowledgments
Thanks to [Kemal Oflazer](http://www.andrew.cmu.edu/user/ko/) for providing us
additional large corpora for Turkish. Many thanks to Reyyan Yeniterzi for providing
us the Turkish NER dataset for evaluation.
Research supported with Cloud TPUs from Google's TensorFlow Research Cloud (TFRC).
Thanks for providing access to the TFRC ❤️
Thanks to the generous support from the [Hugging Face](https://huggingface.co/) team,
it is possible to download both cased and uncased models from their S3 storage 🤗
model_cards/deepset/bert-base-german-cased-oldvocab/README.md deleted 100644 → 0
View file @ 29e45979
---
language: de
license: mit
thumbnail: https://static.tildacdn.com/tild6438-3730-4164-b266-613634323466/german_bert.png
tags:
- exbert
---
<a href="https://huggingface.co/exbert/?model=bert-base-german-cased">
<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
</a>
# German BERT with old vocabulary
For details see the related [FARM issue](https://github.com/deepset-ai/FARM/issues/60).
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
model_cards/deepset/electra-base-squad2/README.md deleted 100644 → 0
View file @ 29e45979
---
datasets:
- squad_v2
---
# electra-base for QA
## Overview
**Language model:** electra-base
**Language:** English
**Downstream-task:** Extractive QA
**Training data:** SQuAD 2.0
**Eval data:** SQuAD 2.0
**Code:** See [example](https://github.com/deepset-ai/FARM/blob/master/examples/question_answering.py) in [FARM](https://github.com/deepset-ai/FARM/blob/master/examples/question_answering.py)
**Infrastructure**: 1x Tesla v100
## Hyperparameters
```
seed=42
batch_size = 32
n_epochs = 5
base_LM_model = "google/electra-base-discriminator"
max_seq_len = 384
learning_rate = 1e-4
lr_schedule = LinearWarmup
warmup_proportion = 0.1
doc_stride=128
max_query_length=64
```
## Performance
Evaluated on the SQuAD 2.0 dev set with the [official eval script](https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/).
```
"exact": 77.30144024256717,
"f1": 81.35438272008543,
"total": 11873,
"HasAns_exact": 74.34210526315789,
"HasAns_f1": 82.45961302894314,
"HasAns_total": 5928,
"NoAns_exact": 80.25231286795626,
"NoAns_f1": 80.25231286795626,
"NoAns_total": 5945
```
## Usage
### In Transformers
```python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/electra-base-squad2"
# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
'question': 'Why is model conversion important?',
'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)
# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
```
### In FARM
```python
from farm.modeling.adaptive_model import AdaptiveModel
from farm.modeling.tokenization import Tokenizer
from farm.infer import Inferencer
model_name = "deepset/electra-base-squad2"
# a) Get predictions
nlp = Inferencer.load(model_name, task_type="question_answering")
QA_input = [{"questions": ["Why is model conversion important?"],
"text": "The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks."}]
res = nlp.inference_from_dicts(dicts=QA_input)
# b) Load model & tokenizer
model = AdaptiveModel.convert_from_transformers(model_name, device="cpu", task_type="question_answering")
tokenizer = Tokenizer.load(model_name)
```
### In haystack
For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in [haystack](https://github.com/deepset-ai/haystack/):
```python
reader = FARMReader(model_name_or_path="deepset/electra-base-squad2")
# or
reader = TransformersReader(model="deepset/electra-base-squad2",tokenizer="deepset/electra-base-squad2")
```
## Authors
Vaishali Pal `vaishali.pal [at] deepset.ai`
Branden Chan: `branden.chan [at] deepset.ai`
Timo Möller: `timo.moeller [at] deepset.ai`
Malte Pietsch: `malte.pietsch [at] deepset.ai`
Tanay Soni: `tanay.soni [at] deepset.ai`
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
model_cards/deepset/gbert-base/README.md deleted 100644 → 0
View file @ 29e45979
---
language: de
license: mit
datasets:
- wikipedia
- OPUS
- OpenLegalData
---
# German BERT base
Released, Oct 2020, this is a German BERT language model trained collaboratively by the makers of the original German BERT (aka "bert-base-german-cased") and the dbmdz BERT (aka bert-base-german-dbmdz-cased). In our [paper](https://arxiv.org/pdf/2010.10906.pdf), we outline the steps taken to train our model and show that it outperforms its predecessors.
## Overview
**Paper:** [here](https://arxiv.org/pdf/2010.10906.pdf)
**Architecture:** BERT base
**Language:** German
## Performance
```
GermEval18 Coarse: 78.17
GermEval18 Fine: 50.90
GermEval14: 87.98
```
See also:
deepset/gbert-base
deepset/gbert-large
deepset/gelectra-base
deepset/gelectra-large
deepset/gelectra-base-generator
deepset/gelectra-large-generator
## Authors
Branden Chan: `branden.chan [at] deepset.ai`
Stefan Schweter: `stefan [at] schweter.eu`
Timo Möller: `timo.moeller [at] deepset.ai`
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
model_cards/deepset/gbert-large/README.md deleted 100644 → 0
View file @ 29e45979
---
language: de
license: mit
datasets:
- wikipedia
- OPUS
- OpenLegalData
- oscar
---
# German BERT large
Released, Oct 2020, this is a German BERT language model trained collaboratively by the makers of the original German BERT (aka "bert-base-german-cased") and the dbmdz BERT (aka bert-base-german-dbmdz-cased). In our [paper](https://arxiv.org/pdf/2010.10906.pdf), we outline the steps taken to train our model and show that it outperforms its predecessors.
## Overview
**Paper:** [here](https://arxiv.org/pdf/2010.10906.pdf)
**Architecture:** BERT large
**Language:** German
## Performance
```
GermEval18 Coarse: 80.08
GermEval18 Fine: 52.48
GermEval14: 88.16
```
See also:
deepset/gbert-base
deepset/gbert-large
deepset/gelectra-base
deepset/gelectra-large
deepset/gelectra-base-generator
deepset/gelectra-large-generator
## Authors
Branden Chan: `branden.chan [at] deepset.ai`
Stefan Schweter: `stefan [at] schweter.eu`
Timo Möller: `timo.moeller [at] deepset.ai`
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
model_cards/deepset/gelectra-base-generator/README.md deleted 100644 → 0
View file @ 29e45979
---
language: de
license: mit
datasets:
- wikipedia
- OPUS
- OpenLegalData
---
# German ELECTRA base generator
Released, Oct 2020, this is the generator component of the German ELECTRA language model trained collaboratively by the makers of the original German BERT (aka "bert-base-german-cased") and the dbmdz BERT (aka bert-base-german-dbmdz-cased). In our [paper](https://arxiv.org/pdf/2010.10906.pdf), we outline the steps taken to train our model.
The generator is useful for performing masking experiments. If you are looking for a regular language model for embedding extraction, or downstream tasks like NER, classification or QA, please use deepset/gelectra-base.
## Overview
**Paper:** [here](https://arxiv.org/pdf/2010.10906.pdf)
**Architecture:** ELECTRA base (generator)
**Language:** German
See also:
deepset/gbert-base
deepset/gbert-large
deepset/gelectra-base
deepset/gelectra-large
deepset/gelectra-base-generator
deepset/gelectra-large-generator
## Authors
Branden Chan: `branden.chan [at] deepset.ai`
Stefan Schweter: `stefan [at] schweter.eu`
Timo Möller: `timo.moeller [at] deepset.ai`
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
model_cards/deepset/gelectra-base/README.md deleted 100644 → 0
View file @ 29e45979
---
language: de
license: mit
datasets:
- wikipedia
- OPUS
- OpenLegalData
---
# German ELECTRA base
Released, Oct 2020, this is a German ELECTRA language model trained collaboratively by the makers of the original German BERT (aka "bert-base-german-cased") and the dbmdz BERT (aka bert-base-german-dbmdz-cased). In our [paper](https://arxiv.org/pdf/2010.10906.pdf), we outline the steps taken to train our model. Our evaluation suggests that this model is somewhat undertrained. For best performance from a base sized model, we recommend deepset/gbert-base
## Overview
**Paper:** [here](https://arxiv.org/pdf/2010.10906.pdf)
**Architecture:** ELECTRA base (discriminator)
**Language:** German
## Performance
```
GermEval18 Coarse: 76.02
GermEval18 Fine: 42.22
GermEval14: 86.02
```
See also:
deepset/gbert-base
deepset/gbert-large
deepset/gelectra-base
deepset/gelectra-large
deepset/gelectra-base-generator
deepset/gelectra-large-generator
## Authors
Branden Chan: `branden.chan [at] deepset.ai`
Stefan Schweter: `stefan [at] schweter.eu`
Timo Möller: `timo.moeller [at] deepset.ai`
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
model_cards/deepset/gelectra-large-generator/README.md deleted 100644 → 0
View file @ 29e45979
---
language: de
license: mit
datasets:
- wikipedia
- OPUS
- OpenLegalData
- oscar
---
# German ELECTRA large generator
Released, Oct 2020, this is the generator component of the German ELECTRA language model trained collaboratively by the makers of the original German BERT (aka "bert-base-german-cased") and the dbmdz BERT (aka bert-base-german-dbmdz-cased). In our [paper](https://arxiv.org/pdf/2010.10906.pdf), we outline the steps taken to train our model.
The generator is useful for performing masking experiments. If you are looking for a regular language model for embedding extraction, or downstream tasks like NER, classification or QA, please use deepset/gelectra-large.
## Overview
**Paper:** [here](https://arxiv.org/pdf/2010.10906.pdf)
**Architecture:** ELECTRA large (generator)
**Language:** German
## Performance
```
GermEval18 Coarse: 80.70
GermEval18 Fine: 55.16
GermEval14: 88.95
```
See also:
deepset/gbert-base
deepset/gbert-large
deepset/gelectra-base
deepset/gelectra-large
deepset/gelectra-base-generator
deepset/gelectra-large-generator
## Authors
Branden Chan: `branden.chan [at] deepset.ai`
Stefan Schweter: `stefan [at] schweter.eu`
Timo Möller: `timo.moeller [at] deepset.ai`
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
model_cards/deepset/gelectra-large/README.md deleted 100644 → 0
View file @ 29e45979
---
language: de
license: mit
datasets:
- wikipedia
- OPUS
- OpenLegalData
- oscar
---
# German ELECTRA large
Released, Oct 2020, this is a German ELECTRA language model trained collaboratively by the makers of the original German BERT (aka "bert-base-german-cased") and the dbmdz BERT (aka bert-base-german-dbmdz-cased). In our [paper](https://arxiv.org/pdf/2010.10906.pdf), we outline the steps taken to train our model and show that this is the state of the art German language model.
## Overview
**Paper:** [here](https://arxiv.org/pdf/2010.10906.pdf)
**Architecture:** ELECTRA large (discriminator)
**Language:** German
## Performance
```
GermEval18 Coarse: 80.70
GermEval18 Fine: 55.16
GermEval14: 88.95
```
See also:
deepset/gbert-base
deepset/gbert-large
deepset/gelectra-base
deepset/gelectra-large
deepset/gelectra-base-generator
deepset/gelectra-large-generator
## Authors
Branden Chan: `branden.chan [at] deepset.ai`
Stefan Schweter: `stefan [at] schweter.eu`
Timo Möller: `timo.moeller [at] deepset.ai`
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
model_cards/deepset/minilm-uncased-squad2/README.md deleted 100644 → 0
View file @ 29e45979
---
datasets:
- squad_v2
---
# MiniLM-L12-H384-uncased for QA
## Overview
**Language model:** microsoft/MiniLM-L12-H384-uncased
**Language:** English
**Downstream-task:** Extractive QA
**Training data:** SQuAD 2.0
**Eval data:** SQuAD 2.0
**Code:** See [example](https://github.com/deepset-ai/FARM/blob/master/examples/question_answering.py) in [FARM](https://github.com/deepset-ai/FARM/blob/master/examples/question_answering.py)
**Infrastructure**: 1x Tesla v100
## Hyperparameters
```
seed=42
batch_size = 12
n_epochs = 4
base_LM_model = "microsoft/MiniLM-L12-H384-uncased"
max_seq_len = 384
learning_rate = 4e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64
grad_acc_steps=4
```
## Performance
Evaluated on the SQuAD 2.0 dev set with the [official eval script](https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/).
```
"exact": 76.13071675229513,
"f1": 79.49786500219953,
"total": 11873,
"HasAns_exact": 78.35695006747639,
"HasAns_f1": 85.10090269418276,
"HasAns_total": 5928,
"NoAns_exact": 73.91084945332211,
"NoAns_f1": 73.91084945332211,
"NoAns_total": 5945
```
## Usage
### In Transformers
```python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/minilm-uncased-squad2"
# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
'question': 'Why is model conversion important?',
'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)
# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
```
### In FARM
```python
from farm.modeling.adaptive_model import AdaptiveModel
from farm.modeling.tokenization import Tokenizer
from farm.infer import Inferencer
model_name = "deepset/minilm-uncased-squad2"
# a) Get predictions
nlp = Inferencer.load(model_name, task_type="question_answering")
QA_input = [{"questions": ["Why is model conversion important?"],
"text": "The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks."}]
res = nlp.inference_from_dicts(dicts=QA_input)
# b) Load model & tokenizer
model = AdaptiveModel.convert_from_transformers(model_name, device="cpu", task_type="question_answering")
tokenizer = Tokenizer.load(model_name)
```
### In haystack
For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in [haystack](https://github.com/deepset-ai/haystack/):
```python
reader = FARMReader(model_name_or_path="deepset/minilm-uncased-squad2")
# or
reader = TransformersReader(model="deepset/minilm-uncased-squad2",tokenizer="deepset/minilm-uncased-squad2")
```
## Authors
Vaishali Pal `vaishali.pal [at] deepset.ai`
Branden Chan: `branden.chan [at] deepset.ai`
Timo Möller: `timo.moeller [at] deepset.ai`
Malte Pietsch: `malte.pietsch [at] deepset.ai`
Tanay Soni: `tanay.soni [at] deepset.ai`
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
model_cards/deepset/quora_dedup_bert_base/README.md deleted 100644 → 0
View file @ 29e45979
This language model is trained using sentence_transformers (https://github.com/UKPLab/sentence-transformers)
Started with bert-base-nli-stsb-mean-tokens
Continue training on quora questions deduplication dataset (https://www.kaggle.com/c/quora-question-pairs)
See train_script.py for script used
Below is the performance over the course of training
epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
0,1000,0.5944576426835938,0.6010801382777033,0.5942803776859142,0.5934485776801595,0.5939676679774666,0.593162725602328,0.5905591590826669,0.5921674789994058
0,2000,0.6404080440207146,0.6416811632113405,0.6384419354012121,0.6352050423100778,0.6379917744471867,0.6347884067391001,0.6410544760582826,0.6379252046791412
0,3000,0.6710168301884945,0.6676529324662036,0.6660195209784969,0.6618423144808695,0.6656461098096684,0.6615366331956389,0.6724401903484759,0.666073727723655
0,4000,0.6886373265097949,0.6808948140300153,0.67907655686838,0.6714218133850957,0.6786809551564443,0.6711577956884357,0.6926435869763303,0.68190855298609
0,5000,0.6991409753700026,0.6919630610321864,0.6991041519437052,0.6868961486499775,0.6987076032270729,0.6865385550504007,0.7035518148330993,0.6916275246101342
0,6000,0.7120367327025509,0.6975005265298305,0.7065567493967201,0.6922375503495235,0.7060005509843024,0.6916475765570651,0.7147094303373102,0.6981390706722722
0,7000,0.7254672394728687,0.7130118465900485,0.7261844956277705,0.7086213543110718,0.7257479964972307,0.7079315661881832,0.728729909455115,0.7122743793160531
0,8000,0.7402421930101399,0.7216774208330149,0.7367901914441078,0.7166256588352043,0.7362607046874481,0.7158881916281887,0.7433902441373252,0.7220998491980078
0,9000,0.7381005358120434,0.7197216844469877,0.7343228719349923,0.7139462687943793,0.7345247569255238,0.7145106206467152,0.7421843672419275,0.720686853053079
0,10000,0.7465436564646095,0.7260327107480364,0.7467524239596304,0.7230195666847953,0.7467721566237211,0.7231367593302213,0.749792199122442,0.7263143296580317
0,11000,0.7521805421706547,0.7323771570146701,0.7530672061250105,0.729223203496722,0.7530616532823367,0.7293818369675622,0.7552399002305836,0.7320808333541338
0,12000,0.7579359969644401,0.7340677616737238,0.7570017235719905,0.7305965412825544,0.7570601853520393,0.730718189957289,0.7611254136080384,0.7351501229591327
0,-1,0.7573407371218097,0.7329952035782198,0.755595312163209,0.7291445551777086,0.7557737117990928,0.7295404703700227,0.7607276219361719,0.7342415455980179
1,1000,0.7619907683805341,0.7374667949734767,0.7629820517114324,0.7330364216044966,0.7628369522755882,0.7331912674450544,0.7658583898073758,0.7381503446695727
1,2000,0.7618972640071228,0.7362151058969478,0.764582212425539,0.7335856230046062,0.7643125513700815,0.7334501607097152,0.7652852805583232,0.7369104639809163
1,3000,0.7687362955240467,0.7404674623181671,0.7708304819979073,0.7380959815601529,0.7707835692712482,0.7379796800453193,0.772074854759756,0.7414513460702766
1,4000,0.7685047787908202,0.7403088288815168,0.7703522257474043,0.7379787888808298,0.7701221475099808,0.7377898546753812,0.7713755359045312,0.7409415801952219
1,5000,0.7696438109797803,0.7410393893292365,0.773270389327895,0.7392953127251652,0.7729880866533291,0.7389853982789335,0.7726236305835863,0.7416278035580925
1,6000,0.7749538363837081,0.7436499342062207,0.774879168058157,0.7401827241766746,0.7745754601165837,0.739763415043146,0.7788801166152383,0.7446249060022169
1,7000,0.7794560817870597,0.7480970176267153,0.7803506944510302,0.7453305130502859,0.7799867949176531,0.7447100155494814,0.7828208193123926,0.7486740690324809
1,8000,0.7855844359073243,0.7496742172376921,0.7828816645965887,0.747176409009761,0.7827584875358967,0.7471037762845532,0.7879159073496309,0.7507349669102151
1,9000,0.7844110753729492,0.7507746252693759,0.7847208586489722,0.7485172180290892,0.7846408087474059,0.748491818820158,0.7872061334510225,0.7514470349769437
1,10000,0.7881311227435004,0.7530048509727403,0.7886917756879734,0.7508018068765787,0.7883332502188707,0.7505037008187275,0.7910707228932787,0.7537200382362567
1,11000,0.7883300109606874,0.7513494487126553,0.7879329130497712,0.749818368689255,0.7876525616593218,0.7494872882301785,0.7911454269743292,0.7522843165147303
1,12000,0.7853334933336618,0.7516809747712728,0.7893895316714998,0.749780492728257,0.7890075986655403,0.7494079715118533,0.7885959664070629,0.7523827940133203
1,-1,0.7887529238148887,0.7534076729932393,0.7896864404801204,0.7513080079201105,0.7894077512343298,0.7510009899066772,0.7919617393746149,0.7542173273241598
2,1000,0.7919209063905188,0.7550167329363414,0.7917464066515253,0.7523043685293455,0.7914371703225378,0.7520285423781206,0.7950297421784158,0.7562599556207076
2,2000,0.7924507768792486,0.7542908512484463,0.7934519001953887,0.7517491515010692,0.7931885648751081,0.751521004535999,0.7951637852162545,0.7551495215642072
2,3000,0.7937606244038364,0.755599577136169,0.7933633347508111,0.7527922999916203,0.7931581019714242,0.7527132061436363,0.797275652800117,0.7569827180764233
2,4000,0.7938389298721445,0.7578716892320315,0.7963783770097079,0.7555928931784702,0.796150381773947,0.7555438771581088,0.7972911620482322,0.759178632650707
2,5000,0.7935330563129844,0.7551129824372304,0.7970775059297484,0.7527285792572385,0.7967359830546507,0.7524478515463257,0.7966395126138969,0.756319220359678
2,6000,0.7929852776759999,0.7525490026774382,0.7952484474454824,0.7503695753216607,0.7950784132079611,0.7503677929234961,0.7956152082976395,0.7535275392698093
2,7000,0.794956504054517,0.756119591765251,0.7982025041673655,0.7532521587180684,0.7980261618830962,0.7532107179960499,0.7983222918908033,0.7571226363678287
2,8000,0.7934568432535339,0.7538336661192452,0.797015698241178,0.7514773358161916,0.7968076980315735,0.7513458838811067,0.7960694134685949,0.754143803399873
2,9000,0.7970040626682157,0.7576497805894974,0.7987855332059015,0.7550996144509958,0.7984693921009676,0.7548260162973456,0.7999509314900626,0.758347143906916
2,10000,0.7979442987735523,0.7585338500791028,0.8018677081664496,0.7557412777548302,0.8015397301245205,0.7552916678886369,0.8007921348414564,0.7589772216225288
2,11000,0.7985519561040211,0.7579986850302035,0.8021236875460913,0.7555826443181872,0.8019861620475348,0.7553763317660516,0.8009230128897853,0.7586541619907702
2,12000,0.7986842143860736,0.7599570950134775,0.8029131054823838,0.7577678644678973,0.8027922603736795,0.7575152095990927,0.8020896747930555,0.7608540869254408
2,-1,0.7994135319568432,0.7596286881516635,0.8022087183675333,0.7570593611974978,0.8020218401019292,0.7567291719729909,0.8026346812258125,0.7603928913647044
3,1000,0.7985505039929134,0.7592588405681144,0.8023296699449267,0.7569345933969436,0.8023622066009718,0.7570237132696928,0.8013054275981851,0.759643838536062
3,2000,0.7995482191699455,0.759205368623176,0.8026859405513612,0.7565709841358819,0.8024845263367439,0.7562920388231202,0.8021318586127523,0.7596496313300967
3,3000,0.7991070423195897,0.7582027696555826,0.8016352550470427,0.7555585819429662,0.8014268261947898,0.7551838327642736,0.8013136081494014,0.7584429477727118
3,4000,0.7999188836884763,0.7586764419322649,0.802987646214278,0.7561111254802977,0.8026549791861386,0.7556463650525692,0.8024068858366156,0.7591238238715613
3,5000,0.7988075932525881,0.7583533823004922,0.8019498750207454,0.755792967372457,0.8016459824731964,0.7553834613587099,0.8015528810821693,0.7589527136833425
3,6000,0.8003341798460688,0.7585432077405799,0.8032464035902267,0.7563722467405277,0.8028695045742804,0.7557626665682309,0.8027937010871594,0.7590404967573696
3,7000,0.799187592384933,0.7579358555659604,0.8028413548398412,0.7555875459131398,0.8025187078191003,0.7551196665011402,0.8018680475193432,0.7585565756912578
3,8000,0.797725037202641,0.757439012042047,0.802048241301358,0.7548888458326453,0.8017608103042271,0.7544606246736175,0.8005479449399782,0.758037452190282
3,9000,0.7990232649360067,0.7573703896772077,0.8021375332910405,0.754873027155089,0.8018733796679427,0.7545680141630304,0.8016400687760605,0.7579461042843499
3,10000,0.7994934439260372,0.758368978248884,0.8035693504115055,0.75619400688862,0.8032990505007025,0.7559016935896375,0.8022819185772518,0.7589558328445544
3,11000,0.8002954591825011,0.758710753096932,0.8043310859792212,0.7566387152306694,0.8040865016706966,0.7564221538891368,0.8030873114870971,0.7592722085543488
3,12000,0.8003726616196549,0.7588056657991931,0.8044000317617518,0.7566146528909147,0.8041705213966136,0.7563419459362758,0.8031760015719815,0.7593194421057111
3,-1,0.8004926728141455,0.7587192194882135,0.8043340929890026,0.756546030526114,0.8041028559910275,0.7563103085106637,0.8032542493776693,0.7592325501951863
model_cards/deepset/roberta-base-squad2-covid/README.md deleted 100644 → 0
View file @ 29e45979
# roberta-base-squad2 for QA on COVID-19
## Overview
**Language model:** deepset/roberta-base-squad2
**Language:** English
**Downstream-task:** Extractive QA
**Training data:** [SQuAD-style CORD-19 annotations from 23rd April](https://github.com/deepset-ai/COVID-QA/blob/master/data/question-answering/200423_covidQA.json)
**Code:** See [example](https://github.com/deepset-ai/FARM/blob/master/examples/question_answering_crossvalidation.py) in [FARM](https://github.com/deepset-ai/FARM)
**Infrastructure**: Tesla v100
## Hyperparameters
```
batch_size = 24
n_epochs = 3
base_LM_model = "deepset/roberta-base-squad2"
max_seq_len = 384
learning_rate = 3e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.1
doc_stride = 128
xval_folds = 5
dev_split = 0
no_ans_boost = -100
```
## Performance
5-fold cross-validation on the data set led to the following results:
**Single EM-Scores:** [0.222, 0.123, 0.234, 0.159, 0.158]
**Single F1-Scores:** [0.476, 0.493, 0.599, 0.461, 0.465]
**Single top\_3\_recall Scores:** [0.827, 0.776, 0.860, 0.771, 0.777]
**XVAL EM:** 0.17890995260663506
**XVAL f1:** 0.49925444207319924
**XVAL top\_3\_recall:** 0.8021327014218009
This model is the model obtained from the **third** fold of the cross-validation.
## Usage
### In Transformers
```python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/roberta-base-squad2-covid"
# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
'question': 'Why is model conversion important?',
'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)
# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
```
### In FARM
```python
from farm.modeling.adaptive_model import AdaptiveModel
from farm.modeling.tokenization import Tokenizer
from farm.infer import Inferencer
model_name = "deepset/roberta-base-squad2-covid"
# a) Get predictions
nlp = Inferencer.load(model_name, task_type="question_answering")
QA_input = [{"questions": ["Why is model conversion important?"],
"text": "The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks."}]
res = nlp.inference_from_dicts(dicts=QA_input, rest_api_schema=True)
# b) Load model & tokenizer
model = AdaptiveModel.convert_from_transformers(model_name, device="cpu", task_type="question_answering")
tokenizer = Tokenizer.load(model_name)
```
### In haystack
For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in [haystack](https://github.com/deepset-ai/haystack/):
```python
reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2-covid")
# or
reader = TransformersReader(model="deepset/roberta-base-squad2",tokenizer="deepset/roberta-base-squad2-covid")
```
## Authors
Branden Chan: `branden.chan [at] deepset.ai`
Timo Möller: `timo.moeller [at] deepset.ai`
Malte Pietsch: `malte.pietsch [at] deepset.ai`
Tanay Soni: `tanay.soni [at] deepset.ai`
Bogdan Kostić: `bogdan.kostic [at] deepset.ai`
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
\ No newline at end of file
model_cards/deepset/roberta-base-squad2-v2/README.md deleted 100644 → 0
View file @ 29e45979
---
datasets:
- squad_v2
---
# roberta-base for QA
## Overview
**Language model:** roberta-base
**Language:** English
**Downstream-task:** Extractive QA
**Training data:** SQuAD 2.0
**Eval data:** SQuAD 2.0
**Code:** See [example](https://github.com/deepset-ai/FARM/blob/master/examples/question_answering.py) in [FARM](https://github.com/deepset-ai/FARM/blob/master/examples/question_answering.py)
**Infrastructure**: 4x Tesla v100
## Hyperparameters
```
batch_size = 96
n_epochs = 2
base_LM_model = "roberta-base"
max_seq_len = 386
learning_rate = 3e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64
```
## Performance
Evaluated on the SQuAD 2.0 dev set with the [official eval script](https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/).
```
"exact": 79.97136359807968
"f1": 83.00449234495325
"total": 11873
"HasAns_exact": 78.03643724696356
"HasAns_f1": 84.11139298441825
"HasAns_total": 5928
"NoAns_exact": 81.90075693860386
"NoAns_f1": 81.90075693860386
"NoAns_total": 5945
```
## Usage
### In Transformers
```python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/roberta-base-squad2-v2"
# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
'question': 'Why is model conversion important?',
'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)
# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
```
### In FARM
```python
from farm.modeling.adaptive_model import AdaptiveModel
from farm.modeling.tokenization import Tokenizer
from farm.infer import Inferencer
model_name = "deepset/roberta-base-squad2-v2"
# a) Get predictions
nlp = Inferencer.load(model_name, task_type="question_answering")
QA_input = [{"questions": ["Why is model conversion important?"],
"text": "The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks."}]
res = nlp.inference_from_dicts(dicts=QA_input, rest_api_schema=True)
# b) Load model & tokenizer
model = AdaptiveModel.convert_from_transformers(model_name, device="cpu", task_type="question_answering")
tokenizer = Tokenizer.load(model_name)
```
### In haystack
For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in [haystack](https://github.com/deepset-ai/haystack/):
```python
reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2-v2")
# or
reader = TransformersReader(model_name_or_path="deepset/roberta-base-squad2-v2",tokenizer="deepset/roberta-base-squad2-v2")
```
## Authors
Branden Chan: `branden.chan [at] deepset.ai`
Timo Möller: `timo.moeller [at] deepset.ai`
Malte Pietsch: `malte.pietsch [at] deepset.ai`
Tanay Soni: `tanay.soni [at] deepset.ai`
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
model_cards/deepset/roberta-base-squad2/README.md deleted 100644 → 0
View file @ 29e45979
---
datasets:
- squad_v2
---
# roberta-base for QA
NOTE: This is version 2 of the model. See [this github issue](https://github.com/deepset-ai/FARM/issues/552) from the FARM repository for an explanation of why we updated. If you'd like to use version 1, specify `revision="v1.0"` when loading the model in Transformers 3.5. For exmaple:
```
model_name = "deepset/roberta-base-squad2"
pipeline(model=model_name, tokenizer=model_name, revision="v1.0", task="question-answering")
```
## Overview
**Language model:** roberta-base
**Language:** English
**Downstream-task:** Extractive QA
**Training data:** SQuAD 2.0
**Eval data:** SQuAD 2.0
**Code:** See [example](https://github.com/deepset-ai/FARM/blob/master/examples/question_answering.py) in [FARM](https://github.com/deepset-ai/FARM/blob/master/examples/question_answering.py)
**Infrastructure**: 4x Tesla v100
## Hyperparameters
```
batch_size = 96
n_epochs = 2
base_LM_model = "roberta-base"
max_seq_len = 386
learning_rate = 3e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64
```
## Performance
Evaluated on the SQuAD 2.0 dev set with the [official eval script](https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/).
```
"exact": 79.97136359807968
"f1": 83.00449234495325
"total": 11873
"HasAns_exact": 78.03643724696356
"HasAns_f1": 84.11139298441825
"HasAns_total": 5928
"NoAns_exact": 81.90075693860386
"NoAns_f1": 81.90075693860386
"NoAns_total": 5945
```
## Usage
### In Transformers
```python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/roberta-base-squad2"
# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
'question': 'Why is model conversion important?',
'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)
# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
```
### In FARM
```python
from farm.modeling.adaptive_model import AdaptiveModel
from farm.modeling.tokenization import Tokenizer
from farm.infer import Inferencer
model_name = "deepset/roberta-base-squad2"
# a) Get predictions
nlp = Inferencer.load(model_name, task_type="question_answering")
QA_input = [{"questions": ["Why is model conversion important?"],
"text": "The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks."}]
res = nlp.inference_from_dicts(dicts=QA_input, rest_api_schema=True)
# b) Load model & tokenizer
model = AdaptiveModel.convert_from_transformers(model_name, device="cpu", task_type="question_answering")
tokenizer = Tokenizer.load(model_name)
```
### In haystack
For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in [haystack](https://github.com/deepset-ai/haystack/):
```python
reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2")
# or
reader = TransformersReader(model_name_or_path="deepset/roberta-base-squad2",tokenizer="deepset/roberta-base-squad2")
```
## Authors
Branden Chan: `branden.chan [at] deepset.ai`
Timo Möller: `timo.moeller [at] deepset.ai`
Malte Pietsch: `malte.pietsch [at] deepset.ai`
Tanay Soni: `tanay.soni [at] deepset.ai`
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
model_cards/deepset/sentence_bert/README.md deleted 100644 → 0
View file @ 29e45979
This is an upload of the bert-base-nli-stsb-mean-tokens pretrained model from the Sentence Transformers Repo (https://github.com/UKPLab/sentence-transformers)
model_cards/deepset/xlm-roberta-large-squad2/README.md deleted 100644 → 0
View file @ 29e45979
---
language: multilingual
tags:
- question-answering
datasets:
- squad_v2
---
# Multilingual XLM-RoBERTa large for QA on various languages
## Overview
**Language model:** xlm-roberta-large
**Language:** Multilingual
**Downstream-task:** Extractive QA
**Training data:** SQuAD 2.0
**Eval data:** SQuAD dev set - German MLQA - German XQuAD
**Training run:** [MLFlow link](https://public-mlflow.deepset.ai/#/experiments/124/runs/3a540e3f3ecf4dd98eae8fc6d457ff20)
**Infrastructure**: 4x Tesla v100
## Hyperparameters
```
batch_size = 32
n_epochs = 3
base_LM_model = "xlm-roberta-large"
max_seq_len = 256
learning_rate = 1e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64
```
## Performance
Evaluated on the SQuAD 2.0 English dev set with the [official eval script](https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/).
```
"exact": 79.45759285774446,
"f1": 83.79259828925511,
"total": 11873,
"HasAns_exact": 71.96356275303644,
"HasAns_f1": 80.6460053117963,
"HasAns_total": 5928,
"NoAns_exact": 86.93019343986543,
"NoAns_f1": 86.93019343986543,
"NoAns_total": 5945
```
Evaluated on German [MLQA: test-context-de-question-de.json](https://github.com/facebookresearch/MLQA)
```
"exact": 49.34691166703564,
"f1": 66.15582561674236,
"total": 4517,
```
Evaluated on German [XQuAD: xquad.de.json](https://github.com/deepmind/xquad)
```
"exact": 61.51260504201681,
"f1": 78.80206098332569,
"total": 1190,
```
## Usage
### In Transformers
```python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/xlm-roberta-large-squad2"
# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
'question': 'Why is model conversion important?',
'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)
# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
```
### In FARM
```python
from farm.modeling.adaptive_model import AdaptiveModel
from farm.modeling.tokenization import Tokenizer
from farm.infer import QAInferencer
model_name = "deepset/xlm-roberta-large-squad2"
# a) Get predictions
nlp = QAInferencer.load(model_name)
QA_input = [{"questions": ["Why is model conversion important?"],
"text": "The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks."}]
res = nlp.inference_from_dicts(dicts=QA_input, rest_api_schema=True)
# b) Load model & tokenizer
model = AdaptiveModel.convert_from_transformers(model_name, device="cpu", task_type="question_answering")
tokenizer = Tokenizer.load(model_name)
```
### In haystack
For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in [haystack](https://github.com/deepset-ai/haystack/):
```python
reader = FARMReader(model_name_or_path="deepset/xlm-roberta-large-squad2")
# or
reader = TransformersReader(model="deepset/xlm-roberta-large-squad2",tokenizer="deepset/xlm-roberta-large-squad2")
```
## Authors
Branden Chan: `branden.chan [at] deepset.ai`
Timo Möller: `timo.moeller [at] deepset.ai`
Malte Pietsch: `malte.pietsch [at] deepset.ai`
Tanay Soni: `tanay.soni [at] deepset.ai`
## About us
![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png)
We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
- [FARM](https://github.com/deepset-ai/FARM)
- [Haystack](https://github.com/deepset-ai/haystack/)
Get in touch:
[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai)
model_cards/digitalepidemiologylab/covid-twitter-bert/README.md deleted 100644 → 0
View file @ 29e45979
---
language: "en"
thumbnail: "https://raw.githubusercontent.com/digitalepidemiologylab/covid-twitter-bert/master/images/COVID-Twitter-BERT_small.png"
tags:
- Twitter
- COVID-19
license: mit
---
# COVID-Twitter-BERT (CT-BERT) v1
:warning: _You may want to use the [v2 model](https://huggingface.co/digitalepidemiologylab/covid-twitter-bert-v2) which was trained on more recent data and yields better performance_ :warning:
BERT-large-uncased model, pretrained on a corpus of messages from Twitter about COVID-19. Find more info on our [GitHub page](https://github.com/digitalepidemiologylab/covid-twitter-bert).
## Overview
This model was trained on 160M tweets collected between January 12 and April 16, 2020 containing at least one of the keywords "wuhan", "ncov", "coronavirus", "covid", or "sars-cov-2". These tweets were filtered and preprocessed to reach a final sample of 22.5M tweets (containing 40.7M sentences and 633M tokens) which were used for training.
This model was evaluated based on downstream classification tasks, but it could be used for any other NLP task which can leverage contextual embeddings.
In order to achieve best results, make sure to use the same text preprocessing as we did for pretraining. This involves replacing user mentions, urls and emojis. You can find a script on our projects [GitHub repo](https://github.com/digitalepidemiologylab/covid-twitter-bert).
## Example usage
```python
tokenizer = AutoTokenizer.from_pretrained("digitalepidemiologylab/covid-twitter-bert")
model = AutoModel.from_pretrained("digitalepidemiologylab/covid-twitter-bert")
```
You can also use the model with the `pipeline` interface:
```python
from transformers import pipeline
import json
pipe = pipeline(task='fill-mask', model='digitalepidemiologylab/covid-twitter-bert-v2')
out = pipe(f"In places with a lot of people, it's a good idea to wear a {pipe.tokenizer.mask_token}")
print(json.dumps(out, indent=4))
[
{
"sequence": "[CLS] in places with a lot of people, it's a good idea to wear a mask [SEP]",
"score": 0.9959408044815063,
"token": 7308,
"token_str": "mask"
},
...
]
```
## References
[1] Martin Müller, Marcel Salaté, Per E Kummervold. "COVID-Twitter-BERT: A Natural Language Processing Model to Analyse COVID-19 Content on Twitter" arXiv preprint arXiv:2005.07503 (2020).
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment