modelId
stringlengths 4
81
| tags
sequence | pipeline_tag
stringclasses 17
values | config
dict | downloads
int64 0
59.7M
| first_commit
timestamp[ns, tz=UTC] | card
stringlengths 51
438k
|
|---|---|---|---|---|---|---|
bert-large-cased-whole-word-masking | [
"pytorch",
"tf",
"jax",
"bert",
"fill-mask",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1810.04805",
"transformers",
"license:apache-2.0",
"autotrain_compatible",
"has_space"
] | fill-mask | {
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 2,316 | 2022-01-12T14:09:07Z | ---
license: apache-2.0
language:
- ar
---
The **AraRoBERTa** models are mono-dialectal Arabic models trained on a country-level dialect. AraRoBERTa uses RoBERTa base config. More details are available in the paper [click](https://aclanthology.org/2022.wanlp-1.24/).
The following are the AraRoBERTa seven dialectal variations:
* [AraRoBERTa-SA](https://huggingface.co/reemalyami/AraRoBERTa-SA): Saudi Arabia (SA) dialect.
* [AraRoBERTa-EGY](https://huggingface.co/reemalyami/AraRoBERTa-EGY): Egypt (EGY) dialect.
* [AraRoBERTa-KU](https://huggingface.co/reemalyami/AraRoBERTa-KU): Kuwait (KU) dialect.
* [AraRoBERTa-OM](https://huggingface.co/reemalyami/AraRoBERTa-OM): Oman (OM) dialect.
* [AraRoBERTa-LB](https://huggingface.co/reemalyami/AraRoBERTa-LB): Lebanon (LB) dialect.
* [AraRoBERTa-JO](https://huggingface.co/reemalyami/AraRoBERTa-JO): Jordan (JO) dialect.
* [AraRoBERTa-DZ](https://huggingface.co/reemalyami/AraRoBERTa-DZ): Algeria (DZ) dialect
# When using the model, please cite our paper:
```python
@inproceedings{alyami-al-zaidy-2022-weakly,
title = "Weakly and Semi-Supervised Learning for {A}rabic Text Classification using Monodialectal Language Models",
author = "AlYami, Reem and Al-Zaidy, Rabah",
booktitle = "Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.24",
pages = "260--272",
}
```
# Contact
**Reem AlYami**: [Linkedin](https://www.linkedin.com/in/reem-alyami/) | <[email protected]> | <[email protected]>
|
bert-large-cased | [
"pytorch",
"tf",
"jax",
"safetensors",
"bert",
"fill-mask",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1810.04805",
"transformers",
"license:apache-2.0",
"autotrain_compatible",
"has_space"
] | fill-mask | {
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 388,769 | 2022-01-12T13:03:19Z | ---
license: apache-2.0
language:
- ar
---
The **AraRoBERTa** models are mono-dialectal Arabic models trained on a country-level dialect. AraRoBERTa uses RoBERTa base config. More details are available in the paper [click](https://aclanthology.org/2022.wanlp-1.24/).
The following are the AraRoBERTa seven dialectal variations:
* [AraRoBERTa-SA](https://huggingface.co/reemalyami/AraRoBERTa-SA): Saudi Arabia (SA) dialect.
* [AraRoBERTa-EGY](https://huggingface.co/reemalyami/AraRoBERTa-EGY): Egypt (EGY) dialect.
* [AraRoBERTa-KU](https://huggingface.co/reemalyami/AraRoBERTa-KU): Kuwait (KU) dialect.
* [AraRoBERTa-OM](https://huggingface.co/reemalyami/AraRoBERTa-OM): Oman (OM) dialect.
* [AraRoBERTa-LB](https://huggingface.co/reemalyami/AraRoBERTa-LB): Lebanon (LB) dialect.
* [AraRoBERTa-JO](https://huggingface.co/reemalyami/AraRoBERTa-JO): Jordan (JO) dialect.
* [AraRoBERTa-DZ](https://huggingface.co/reemalyami/AraRoBERTa-DZ): Algeria (DZ) dialect
# When using the model, please cite our paper:
```python
@inproceedings{alyami-al-zaidy-2022-weakly,
title = "Weakly and Semi-Supervised Learning for {A}rabic Text Classification using Monodialectal Language Models",
author = "AlYami, Reem and Al-Zaidy, Rabah",
booktitle = "Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.24",
pages = "260--272",
}
```
# Contact
**Reem AlYami**: [Linkedin](https://www.linkedin.com/in/reem-alyami/) | <[email protected]> | <[email protected]>
|
bert-large-uncased-whole-word-masking-finetuned-squad | [
"pytorch",
"tf",
"jax",
"safetensors",
"bert",
"question-answering",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1810.04805",
"transformers",
"license:apache-2.0",
"autotrain_compatible",
"has_space"
] | question-answering | {
"architectures": [
"BertForQuestionAnswering"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 480,510 | 2022-01-12T14:07:39Z | ---
license: apache-2.0
language:
- ar
---
The **AraRoBERTa** models are mono-dialectal Arabic models trained on a country-level dialect. AraRoBERTa uses RoBERTa base config. More details are available in the paper [click](https://aclanthology.org/2022.wanlp-1.24/).
The following are the AraRoBERTa seven dialectal variations:
* [AraRoBERTa-SA](https://huggingface.co/reemalyami/AraRoBERTa-SA): Saudi Arabia (SA) dialect.
* [AraRoBERTa-EGY](https://huggingface.co/reemalyami/AraRoBERTa-EGY): Egypt (EGY) dialect.
* [AraRoBERTa-KU](https://huggingface.co/reemalyami/AraRoBERTa-KU): Kuwait (KU) dialect.
* [AraRoBERTa-OM](https://huggingface.co/reemalyami/AraRoBERTa-OM): Oman (OM) dialect.
* [AraRoBERTa-LB](https://huggingface.co/reemalyami/AraRoBERTa-LB): Lebanon (LB) dialect.
* [AraRoBERTa-JO](https://huggingface.co/reemalyami/AraRoBERTa-JO): Jordan (JO) dialect.
* [AraRoBERTa-DZ](https://huggingface.co/reemalyami/AraRoBERTa-DZ): Algeria (DZ) dialect
# When using the model, please cite our paper:
```python
@inproceedings{alyami-al-zaidy-2022-weakly,
title = "Weakly and Semi-Supervised Learning for {A}rabic Text Classification using Monodialectal Language Models",
author = "AlYami, Reem and Al-Zaidy, Rabah",
booktitle = "Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.24",
pages = "260--272",
}
```
# Contact
**Reem AlYami**: [Linkedin](https://www.linkedin.com/in/reem-alyami/) | <[email protected]> | <[email protected]>
|
bert-large-uncased | [
"pytorch",
"tf",
"jax",
"safetensors",
"bert",
"fill-mask",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1810.04805",
"transformers",
"license:apache-2.0",
"autotrain_compatible",
"has_space"
] | fill-mask | {
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 1,058,496 | 2022-01-12T14:08:32Z | ---
license: apache-2.0
language:
- ar
---
The **AraRoBERTa** models are mono-dialectal Arabic models trained on a country-level dialect. AraRoBERTa uses RoBERTa base config. More details are available in the paper [click](https://aclanthology.org/2022.wanlp-1.24/).
The following are the AraRoBERTa seven dialectal variations:
* AraRoBERTa-SA: Saudi Arabia (SA) dialect.
* AraRoBERTa-EGY: Egypt (EGY) dialect.
* AraRoBERTa-KU: Kuwait (KU) dialect.
* AraRoBERTa-OM: Oman (OM) dialect.
* AraRoBERTa-LB: Lebanon (LB) dialect.
* AraRoBERTa-JO: Jordan (JO) dialect.
* AraRoBERTa-DZ: Algeria (DZ) dialect
# When using the model, please cite our paper:
```python
@inproceedings{alyami-al-zaidy-2022-weakly,
title = "Weakly and Semi-Supervised Learning for {A}rabic Text Classification using Monodialectal Language Models",
author = "AlYami, Reem and Al-Zaidy, Rabah",
booktitle = "Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.24",
pages = "260--272",
}
```
# Contact
**Reem AlYami**: [Linkedin](https://www.linkedin.com/in/reem-alyami/) | <[email protected]> | <[email protected]>
|
camembert-base | [
"pytorch",
"tf",
"safetensors",
"camembert",
"fill-mask",
"fr",
"dataset:oscar",
"arxiv:1911.03894",
"transformers",
"license:mit",
"autotrain_compatible",
"has_space"
] | fill-mask | {
"architectures": [
"CamembertForMaskedLM"
],
"model_type": "camembert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 1,440,898 | 2022-01-10T21:57:12Z | ---
license: apache-2.0
language:
- ar
---
The **AraRoBERTa** models are mono-dialectal Arabic models trained on a country-level dialect. AraRoBERTa uses RoBERTa base config. More details are available in the paper [click](https://aclanthology.org/2022.wanlp-1.24/).
The following are the AraRoBERTa seven dialectal variations:
* [AraRoBERTa-SA](https://huggingface.co/reemalyami/AraRoBERTa-SA): Saudi Arabia (SA) dialect.
* [AraRoBERTa-EGY](https://huggingface.co/reemalyami/AraRoBERTa-EGY): Egypt (EGY) dialect.
* [AraRoBERTa-KU](https://huggingface.co/reemalyami/AraRoBERTa-KU): Kuwait (KU) dialect.
* [AraRoBERTa-OM](https://huggingface.co/reemalyami/AraRoBERTa-OM): Oman (OM) dialect.
* [AraRoBERTa-LB](https://huggingface.co/reemalyami/AraRoBERTa-LB): Lebanon (LB) dialect.
* [AraRoBERTa-JO](https://huggingface.co/reemalyami/AraRoBERTa-JO): Jordan (JO) dialect.
* [AraRoBERTa-DZ](https://huggingface.co/reemalyami/AraRoBERTa-DZ): Algeria (DZ) dialect
# When using the model, please cite our paper:
```python
@inproceedings{alyami-al-zaidy-2022-weakly,
title = "Weakly and Semi-Supervised Learning for {A}rabic Text Classification using Monodialectal Language Models",
author = "AlYami, Reem and Al-Zaidy, Rabah",
booktitle = "Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.24",
pages = "260--272",
}
```
# Contact
**Reem AlYami**: [Linkedin](https://www.linkedin.com/in/reem-alyami/) | <[email protected]> | <[email protected]>
|
distilbert-base-cased | [
"pytorch",
"tf",
"onnx",
"distilbert",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1910.01108",
"transformers",
"license:apache-2.0",
"has_space"
] | null | {
"architectures": null,
"model_type": "distilbert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 574,859 | 2022-02-06T01:33:40Z | ---
license: apache-2.0
language:
- as
tags:
- generated_from_trainer
- robust-speech-event
- hf-asr-leaderboard
datasets:
- common_voice
model-index:
- name: wav2vec2-large-xls-r-300m-as
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# wav2vec2-large-xls-r-300m-as
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8318
- Wer: 0.5174
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.12
- num_epochs: 120
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 4.882 | 25.0 | 400 | 1.2290 | 0.8182 |
| 0.8275 | 50.0 | 800 | 0.6835 | 0.5398 |
| 0.337 | 75.0 | 1200 | 0.7789 | 0.5107 |
| 0.2113 | 100.0 | 1600 | 0.8318 | 0.5174 |
### Framework versions
- Transformers 4.16.2
- Pytorch 1.10.1+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.10.3
### Test Evaluation
Common Voice Assamese Test Set (v7.0)
- WER: 0.7224
- CER: 0.2882 |
A-bhimany-u08/bert-base-cased-qqp | [
"pytorch",
"bert",
"text-classification",
"dataset:qqp",
"transformers"
] | text-classification | {
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 138 | 2022-01-19T18:41:06Z | ---
tags:
- conversational
---
# Childe Chatbot Model |
Adnan/UrduNewsHeadlines | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: mt5-small-finetuned-src-to-trg
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mt5-small-finetuned-src-to-trg
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
| No log | 1.0 | 40 | nan | 0.1737 | 3.1818 |
### Framework versions
- Transformers 4.14.1
- Pytorch 1.6.0
- Datasets 1.16.1
- Tokenizers 0.10.3
|
AethiQs-Max/aethiqs-base_bertje-data_rotterdam-epochs_30-epoch_30 | [
"pytorch",
"bert",
"fill-mask",
"transformers",
"autotrain_compatible"
] | fill-mask | {
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 8 | null | ---
language:
- da
license: cc0-1.0
tasks:
- automatic-speech-recognition
datasets:
- common_voice_8_0
metrics:
- wer
model-index:
- name: kblab-voxrex-wav2vec2-large-cv8-da
results:
- task:
type: automatic-speech-recognition
dataset:
type: mozilla-foundation/common_voice_8_0
args: da
name: Danish Common Voice 8.0
metrics:
- type: wer
value: 30.51
- task:
type: automatic-speech-recognition
dataset:
type: Alvenir/alvenir_asr_da_eval
name: Alvenir ASR test dataset
metrics:
- type: wer
value: 28.33
---
# KBLab-VoxRex-Wav2vec2-large-CV8-da
## Model description
This model is a fine-tuned version of the Swedish acoustic model [KBLab/wav2vec2-large-voxrex](https://huggingface.co/KBLab/wav2vec2-large-voxrex) on the Danish part of [Common Voice 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0), containing ~6 crowdsourced hours of read-aloud Danish speech.
## Performance
The model achieves the following WER scores (lower is better):
| **Dataset** | **WER without LM** | **WER with 5-gram LM** |
| :---: | ---: | ---: |
| [Danish part of Common Voice 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0/viewer/da/train) | 37.63 | 30.51 |
| [Alvenir test set](https://huggingface.co/datasets/Alvenir/alvenir_asr_da_eval) | 35.75 | 28.33 | |
Aimendo/Triage | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
language:
- en
tags:
- image-to-text
license: mit
datasets:
- coco2017
---
# Vit2-DistilGPT2
This model takes in an image and outputs a caption. It was trained using the Coco dataset and the full training script can be found in [this kaggle kernel](https://www.kaggle.com/sachin/visionencoderdecoder-model-training)
## Usage
```python
import Image
from transformers import AutoModel, GPT2Tokenizer, ViTFeatureExtractor
model = AutoModel.from_pretrained("sachin/vit2distilgpt2")
vit_feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224-in21k")
# make sure GPT2 appends EOS in begin and end
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
outputs = [self.bos_token_id] + token_ids_0 + [self.eos_token_id]
return outputs
GPT2Tokenizer.build_inputs_with_special_tokens = build_inputs_with_special_tokens
gpt2_tokenizer = GPT2Tokenizer.from_pretrained("distilgpt2")
# set pad_token_id to unk_token_id -> be careful here as unk_token_id == eos_token_id == bos_token_id
gpt2_tokenizer.pad_token = gpt2_tokenizer.unk_token
image = (Image.open(image_path).convert("RGB"), return_tensors="pt").pixel_values
encoder_outputs = model.generate(image.unsqueeze(0))
generated_sentences = gpt2_tokenizer.batch_decode(encoder_outputs, skip_special_tokens=True)
```
Note that the output sentence may be repeated, hence a post processing step may be required.
## Bias Warning
This model may be biased due to dataset, lack of long training and the model itself. The following gender bias is an example.
## Results
<iframe src="https://wandb.ai/sachinruk/Vit2GPT2/reports/Shared-panel-22-01-27-23-01-56--VmlldzoxNDkyMTM3?highlightShare" style="border:none;height:1024px;width:100%">
|
Akbarariza/Anjar | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
language:
- hi
- en
- multilingual
license: mit
tags:
- codeswitching
- hindi-english
- pos
datasets:
- lince
---
# codeswitch-hineng-pos-lince
This is a pretrained model for **Part of Speech Tagging** of `hindi-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home)
This model is trained for this below repository.
[https://github.com/sagorbrur/codeswitch](https://github.com/sagorbrur/codeswitch)
To install codeswitch:
```
pip install codeswitch
```
## Part-of-Speech Tagging of Hindi-English Mixed Data
* **Method-1**
```py
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-hineng-pos-lince")
model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-hineng-pos-lince")
pos_model = pipeline('ner', model=model, tokenizer=tokenizer)
pos_model("put any hindi english code-mixed sentence")
```
* **Method-2**
```py
from codeswitch.codeswitch import POS
pos = POS('hin-eng')
text = "" # your mixed sentence
result = pos.tag(text)
print(result)
```
|
Akira-Yana/distilbert-base-uncased-finetuned-cola | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
language:
- ne
- en
- multilingual
license: mit
tags:
- codeswitching
- nepali-english
- language-identification
datasets:
- lince
---
# codeswitch-nepeng-lid-lince
This is a pretrained model for **language identification** of `nepali-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home).
This model is trained for this below repository.
[https://github.com/sagorbrur/codeswitch](https://github.com/sagorbrur/codeswitch)
To install codeswitch:
```
pip install codeswitch
```
## Identify Language
* **Method-1**
```py
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-nepeng-lid-lince")
model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-nepeng-lid-lince")
lid_model = pipeline('ner', model=model, tokenizer=tokenizer)
lid_model("put any nepali english code-mixed sentence")
```
* **Method-2**
```py
from codeswitch.codeswitch import LanguageIdentification
lid = LanguageIdentification('nep-eng')
text = "" # your code-mixed sentence
result = lid.identify(text)
print(result)
```
|
Alaeddin/convbert-base-turkish-ner-cased | [
"pytorch",
"convbert",
"token-classification",
"transformers",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"ConvBertForTokenClassification"
],
"model_type": "convbert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 9 | null | # random-albert-base-v2
We introduce random-albert-base-v2, which is a unpretrained version of Albert model. The weight of random-albert-base-v2 is randomly initiated and this can be particularly useful when we aim to train a language model from scratch or benchmark the effect of pretraining.
It's important to note that tokenizer of random-albert-base-v2 is the same as albert-base-v2 because it's not a trivial task to get a random tokenizer and it's less meaningful compared to the random weight.
A debatable advantage of pulling random-albert-base-v2 from Huggingface is to avoid using random seed in order to obtain the same randomness at each time.
The code to obtain a such random model:
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
def get_blank_model_from_hf(model_name="bert-base-cased"):
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=5)
tokenizer = AutoTokenizer.from_pretrained(model_name)
model.base_model.init_weights()
model_name = "random-" + model_name
base_model= model.base_model
return base_model, tokenizer, model_name
```
|
AlanDev/test | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | 2021-07-08T12:51:37Z | # random-roberta-base
We introduce random-roberta-base, which is a unpretrained version of RoBERTa model. The weight of random-roberta-base is randomly initiated and this can be particularly useful when we aim to train a language model from scratch or benchmark the effect of pretraining.
It's important to note that tokenizer of random-roberta-base is the same as roberta-base because it's not a trivial task to get a random tokenizer and it's less meaningful compared to the random weight.
A debatable advantage of pulling random-roberta-base from Huggingface is to avoid using random seed in order to obtain the same randomness at each time.
The code to obtain such a random model:
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
def get_blank_model_from_hf(model_name="bert-base-cased"):
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=5)
tokenizer = AutoTokenizer.from_pretrained(model_name)
model.base_model.init_weights()
model_name = "random-" + model_name
base_model= model.base_model
return base_model, tokenizer, model_name
```
|
AlbertHSU/BertTEST | [
"pytorch"
] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 8 | 2021-07-08T13:16:30Z | # random-roberta-mini
We introduce random-roberta-mini, which is a unpretrained version of a mini RoBERTa model(4 layer and 256 heads). The weight of random-roberta-mini is randomly initiated and this can be particularly useful when we aim to train a language model from scratch or benchmark the effect of pretraining.
It's important to note that tokenizer of random-roberta-mini is the same as roberta-base because it's not a trivial task to get a random tokenizer and it's less meaningful compared to the random weight.
A debatable advantage of pulling random-roberta-mini from Huggingface is to avoid using random seed in order to obtain the same randomness at each time.
The code to obtain such random model:
```python
from transformers import RobertaConfig, RobertaModel
def get_custom_blank_roberta(h=768, l=12):
# Initializing a RoBERTa configuration
configuration = RobertaConfig(num_attention_heads=h, num_hidden_layers=l)
# Initializing a model from the configuration
model = RobertaModel(configuration)
return model
rank="mini"
h=256
l=4
model_type = "roberta"
tokenizer = AutoTokenizer.from_pretrained("roberta-base")
model_name ="random-"+model_type+"-"+rank
model = get_custom_blank_roberta(h, l)
```
|
AlbertHSU/ChineseFoodBert | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 15 | null | # random-roberta-tiny
We introduce random-roberta-tiny, which is a unpretrained version of a mini RoBERTa model(2 layer and 128 heads). The weight of random-roberta-tiny is randomly initiated and this can be particularly useful when we aim to train a language model from scratch or benchmark the effect of pretraining.
It's important to note that tokenizer of random-roberta-tiny is the same as roberta-base because it's not a trivial task to get a random tokenizer and it's less meaningful compared to the random weight.
A debatable advantage of pulling random-roberta-tiny from Huggingface is to avoid using random seed in order to obtain the same randomness at each time.
The code to obtain such random model:
```python
from transformers import RobertaConfig, RobertaModel
def get_custom_blank_roberta(h=768, l=12):
# Initializing a RoBERTa configuration
configuration = RobertaConfig(num_attention_heads=h, num_hidden_layers=l)
# Initializing a model from the configuration
model = RobertaModel(configuration)
return model
rank="tiny"
h=128
l=2
model_type = "roberta"
tokenizer = AutoTokenizer.from_pretrained("roberta-base")
model_name ="random-"+model_type+"-"+rank
model = get_custom_blank_roberta(h, l)
```
|
Aleksandar/bert-srb-base-cased-oscar | [
"pytorch",
"bert",
"fill-mask",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] | fill-mask | {
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 7 | 2022-01-29T14:15:05Z | ---
license: apache-2.0
tags:
- image-classification
- vision
datasets:
- imagenet
---
# PoolFormer (M48 model)
PoolFormer model trained on ImageNet-1k (1 million images, 1,000 classes) at resolution 224x224. It was first introduced in the paper [MetaFormer is Actually What You Need for Vision](https://arxiv.org/abs/2111.11418) by Yu et al. and first released in [this repository](https://github.com/sail-sg/poolformer).
## Model description
PoolFormer is a model that replaces attention token mixer in transfomrers with extremely simple operator, pooling.
Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in transformers can be replaced by spatial MLPs and the resulted models still perform quite well. Based on this observation, we hypothesize that the general architecture of the transformers, instead of the specific token mixer module, is more essential to the model's performance. To verify this, we deliberately replace the attention module in transformers with an embarrassingly simple spatial pooling operator to conduct only the most basic token mixing. Surprisingly, we observe that the derived model, termed as PoolFormer, achieves competitive performance on multiple computer vision tasks. For example, on ImageNet-1K, PoolFormer achieves 82.1% top-1 accuracy, surpassing well-tuned vision transformer/MLP-like baselines DeiT-B/ResMLP-B24 by 0.3%/1.1% accuracy with 35%/52% fewer parameters and 48%/60% fewer MACs. The effectiveness of PoolFormer verifies our hypothesis and urges us to initiate the concept of "MetaFormer", a general architecture abstracted from transformers without specifying the token mixer. Based on the extensive experiments, we argue that MetaFormer is the key player in achieving superior results for recent transformer and MLP-like models on vision tasks. This work calls for more future research dedicated to improving MetaFormer instead of focusing on the token mixer modules. Additionally, our proposed PoolFormer could serve as a starting baseline for future MetaFormer architecture design.
## Intended uses & limitations
You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=sail/poolformer) to look for fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
```python
from transformers import PoolFormerFeatureExtractor, PoolFormerForImageClassification
from PIL import Image
import requests
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
feature_extractor = PoolFormerFeatureExtractor.from_pretrained('sail/poolformer_m48')
model = PoolFormerForImageClassification.from_pretrained('sail/poolformer_m48')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
# model predicts one of the 1000 ImageNet classes
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])
```
Currently, both the feature extractor and model support PyTorch.
## Training data
The poolformer model was trained on [ImageNet-1k](http://www.image-net.org/challenges/LSVRC/2012/), a dataset consisting of 1 million images and 1k classes.
## Training procedure
### Preprocessing
The exact details of preprocessing of images during training/validation can be found [here](https://github.com/sail-sg/poolformer/blob/main/train.py#L529-L572).
### Pretraining
The model was trained on TPU-v3s. Training resolution is 224. For all hyperparameters (such as batch size and learning rate), please refer to the original paper.
## Evaluation results
| Model | ImageNet top-1 accuracy | # params | URL |
|---------------------------------------|-------------------------|----------|------------------------------------------------------------------|
| PoolFormer-S12 | 77.2 | 12M | https://huggingface.co/sail/poolformer_s12 |
| PoolFormer-S24 | 80.3 | 21M | https://huggingface.co/sail/poolformer_s24 |
| PoolFormer-S36 | 81.4 | 31M | https://huggingface.co/sail/poolformer_s36 |
| PoolFormer-M36 | 82.1 | 56M | https://huggingface.co/sail/poolformer_m36 |
| **PoolFormer-M48** | **82.5** | **73M** | **https://huggingface.co/sail/poolformer_m48** |
### BibTeX entry and citation info
```bibtex
@article{yu2021metaformer,
title={MetaFormer is Actually What You Need for Vision},
author={Yu, Weihao and Luo, Mi and Zhou, Pan and Si, Chenyang and Zhou, Yichen and Wang, Xinchao and Feng, Jiashi and Yan, Shuicheng},
journal={arXiv preprint arXiv:2111.11418},
year={2021}
}
``` |
Aleksandar/bert-srb-ner-setimes-lr | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
license: apache-2.0
tags:
- image-classification
- vision
datasets:
- imagenet
---
# PoolFormer (S12 model)
PoolFormer model trained on ImageNet-1k (1 million images, 1,000 classes) at resolution 224x224. It was first introduced in the paper [MetaFormer is Actually What You Need for Vision](https://arxiv.org/abs/2111.11418) by Yu et al. and first released in [this repository](https://github.com/sail-sg/poolformer).
## Model description
PoolFormer is a model that replaces attention token mixer in transfomrers with extremely simple operator, pooling.
Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in transformers can be replaced by spatial MLPs and the resulted models still perform quite well. Based on this observation, we hypothesize that the general architecture of the transformers, instead of the specific token mixer module, is more essential to the model's performance. To verify this, we deliberately replace the attention module in transformers with an embarrassingly simple spatial pooling operator to conduct only the most basic token mixing. Surprisingly, we observe that the derived model, termed as PoolFormer, achieves competitive performance on multiple computer vision tasks. For example, on ImageNet-1K, PoolFormer achieves 82.1% top-1 accuracy, surpassing well-tuned vision transformer/MLP-like baselines DeiT-B/ResMLP-B24 by 0.3%/1.1% accuracy with 35%/52% fewer parameters and 48%/60% fewer MACs. The effectiveness of PoolFormer verifies our hypothesis and urges us to initiate the concept of "MetaFormer", a general architecture abstracted from transformers without specifying the token mixer. Based on the extensive experiments, we argue that MetaFormer is the key player in achieving superior results for recent transformer and MLP-like models on vision tasks. This work calls for more future research dedicated to improving MetaFormer instead of focusing on the token mixer modules. Additionally, our proposed PoolFormer could serve as a starting baseline for future MetaFormer architecture design.
## Intended uses & limitations
You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=sail/poolformer) to look for fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
```python
from transformers import PoolFormerFeatureExtractor, PoolFormerForImageClassification
from PIL import Image
import requests
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
feature_extractor = PoolFormerFeatureExtractor.from_pretrained('sail/poolformer_s12')
model = PoolFormerForImageClassification.from_pretrained('sail/poolformer_s12')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
# model predicts one of the 1000 ImageNet classes
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])
```
Currently, both the feature extractor and model support PyTorch.
## Training data
The poolformer model was trained on [ImageNet-1k](http://www.image-net.org/challenges/LSVRC/2012/), a dataset consisting of 1 million images and 1k classes.
## Training procedure
### Preprocessing
The exact details of preprocessing of images during training/validation can be found [here](https://github.com/sail-sg/poolformer/blob/main/train.py#L529-L572).
### Pretraining
The model was trained on TPU-v3s. Training resolution is 224. For all hyperparameters (such as batch size and learning rate), please refer to the original paper.
## Evaluation results
| Model | ImageNet top-1 accuracy | # params | URL |
|---------------------------------------|-------------------------|----------|------------------------------------------------------------------|
| **PoolFormer-S12** | **77.2** | **12M** | **https://huggingface.co/sail/poolformer_s12** |
| PoolFormer-S24 | 80.3 | 21M | https://huggingface.co/sail/poolformer_s24 |
| PoolFormer-S36 | 81.4 | 31M | https://huggingface.co/sail/poolformer_s36 |
| PoolFormer-M36 | 82.1 | 56M | https://huggingface.co/sail/poolformer_m36 |
| PoolFormer-M48 | 82.5 | 73M | https://huggingface.co/sail/poolformer_m48 |
### BibTeX entry and citation info
```bibtex
@article{yu2021metaformer,
title={MetaFormer is Actually What You Need for Vision},
author={Yu, Weihao and Luo, Mi and Zhou, Pan and Si, Chenyang and Zhou, Yichen and Wang, Xinchao and Feng, Jiashi and Yan, Shuicheng},
journal={arXiv preprint arXiv:2111.11418},
year={2021}
}
``` |
Aleksandar/bert-srb-ner-setimes | [
"pytorch",
"bert",
"token-classification",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"BertForTokenClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 8 | null | ---
license: apache-2.0
tags:
- image-classification
- vision
datasets:
- imagenet
---
# PoolFormer (S24 model)
PoolFormer model trained on ImageNet-1k (1 million images, 1,000 classes) at resolution 224x224. It was first introduced in the paper [MetaFormer is Actually What You Need for Vision](https://arxiv.org/abs/2111.11418) by Yu et al. and first released in [this repository](https://github.com/sail-sg/poolformer).
## Model description
PoolFormer is a model that replaces attention token mixer in transfomrers with extremely simple operator, pooling.
Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in transformers can be replaced by spatial MLPs and the resulted models still perform quite well. Based on this observation, we hypothesize that the general architecture of the transformers, instead of the specific token mixer module, is more essential to the model's performance. To verify this, we deliberately replace the attention module in transformers with an embarrassingly simple spatial pooling operator to conduct only the most basic token mixing. Surprisingly, we observe that the derived model, termed as PoolFormer, achieves competitive performance on multiple computer vision tasks. For example, on ImageNet-1K, PoolFormer achieves 82.1% top-1 accuracy, surpassing well-tuned vision transformer/MLP-like baselines DeiT-B/ResMLP-B24 by 0.3%/1.1% accuracy with 35%/52% fewer parameters and 48%/60% fewer MACs. The effectiveness of PoolFormer verifies our hypothesis and urges us to initiate the concept of "MetaFormer", a general architecture abstracted from transformers without specifying the token mixer. Based on the extensive experiments, we argue that MetaFormer is the key player in achieving superior results for recent transformer and MLP-like models on vision tasks. This work calls for more future research dedicated to improving MetaFormer instead of focusing on the token mixer modules. Additionally, our proposed PoolFormer could serve as a starting baseline for future MetaFormer architecture design.
## Intended uses & limitations
You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=sail/poolformer) to look for fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
```python
from transformers import PoolFormerFeatureExtractor, PoolFormerForImageClassification
from PIL import Image
import requests
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
feature_extractor = PoolFormerFeatureExtractor.from_pretrained('sail/poolformer_s24')
model = PoolFormerForImageClassification.from_pretrained('sail/poolformer_s24')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
# model predicts one of the 1000 ImageNet classes
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])
```
Currently, both the feature extractor and model support PyTorch.
## Training data
The poolformer model was trained on [ImageNet-1k](http://www.image-net.org/challenges/LSVRC/2012/), a dataset consisting of 1 million images and 1k classes.
## Training procedure
### Preprocessing
The exact details of preprocessing of images during training/validation can be found [here](https://github.com/sail-sg/poolformer/blob/main/train.py#L529-L572).
### Pretraining
The model was trained on TPU-v3s. Training resolution is 224. For all hyperparameters (such as batch size and learning rate), please refer to the original paper.
## Evaluation results
| Model | ImageNet top-1 accuracy | # params | URL |
|---------------------------------------|-------------------------|----------|------------------------------------------------------------------|
| PoolFormer-S12 | 77.2 | 12M | https://huggingface.co/sail/poolformer_s12 |
| **PoolFormer-S24** | **80.3** | **21M** | **https://huggingface.co/sail/poolformer_s24** |
| PoolFormer-S36 | 81.4 | 31M | https://huggingface.co/sail/poolformer_s36 |
| PoolFormer-M36 | 82.1 | 56M | https://huggingface.co/sail/poolformer_m36 |
| PoolFormer-M48 | 82.5 | 73M | https://huggingface.co/sail/poolformer_m48 |
### BibTeX entry and citation info
```bibtex
@article{yu2021metaformer,
title={MetaFormer is Actually What You Need for Vision},
author={Yu, Weihao and Luo, Mi and Zhou, Pan and Si, Chenyang and Zhou, Yichen and Wang, Xinchao and Feng, Jiashi and Yan, Shuicheng},
journal={arXiv preprint arXiv:2111.11418},
year={2021}
}
``` |
Aleksandar/bert-srb-ner | [
"pytorch",
"bert",
"token-classification",
"dataset:wikiann",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"BertForTokenClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 4 | null | ---
license: apache-2.0
tags:
- image-classification
- vision
datasets:
- imagenet
---
# PoolFormer (S36 model)
PoolFormer model trained on ImageNet-1k (1 million images, 1,000 classes) at resolution 224x224. It was first introduced in the paper [MetaFormer is Actually What You Need for Vision](https://arxiv.org/abs/2111.11418) by Yu et al. and first released in [this repository](https://github.com/sail-sg/poolformer).
## Model description
PoolFormer is a model that replaces attention token mixer in transfomrers with extremely simple operator, pooling.
Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in transformers can be replaced by spatial MLPs and the resulted models still perform quite well. Based on this observation, we hypothesize that the general architecture of the transformers, instead of the specific token mixer module, is more essential to the model's performance. To verify this, we deliberately replace the attention module in transformers with an embarrassingly simple spatial pooling operator to conduct only the most basic token mixing. Surprisingly, we observe that the derived model, termed as PoolFormer, achieves competitive performance on multiple computer vision tasks. For example, on ImageNet-1K, PoolFormer achieves 82.1% top-1 accuracy, surpassing well-tuned vision transformer/MLP-like baselines DeiT-B/ResMLP-B24 by 0.3%/1.1% accuracy with 35%/52% fewer parameters and 48%/60% fewer MACs. The effectiveness of PoolFormer verifies our hypothesis and urges us to initiate the concept of "MetaFormer", a general architecture abstracted from transformers without specifying the token mixer. Based on the extensive experiments, we argue that MetaFormer is the key player in achieving superior results for recent transformer and MLP-like models on vision tasks. This work calls for more future research dedicated to improving MetaFormer instead of focusing on the token mixer modules. Additionally, our proposed PoolFormer could serve as a starting baseline for future MetaFormer architecture design.
## Intended uses & limitations
You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=sail/poolformer) to look for fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
```python
from transformers import PoolFormerFeatureExtractor, PoolFormerForImageClassification
from PIL import Image
import requests
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
feature_extractor = PoolFormerFeatureExtractor.from_pretrained('sail/poolformer_s36')
model = PoolFormerForImageClassification.from_pretrained('sail/poolformer_s36')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
# model predicts one of the 1000 ImageNet classes
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])
```
Currently, both the feature extractor and model support PyTorch.
## Training data
The poolformer model was trained on [ImageNet-1k](http://www.image-net.org/challenges/LSVRC/2012/), a dataset consisting of 1 million images and 1k classes.
## Training procedure
### Preprocessing
The exact details of preprocessing of images during training/validation can be found [here](https://github.com/sail-sg/poolformer/blob/main/train.py#L529-L572).
### Pretraining
The model was trained on TPU-v3s. Training resolution is 224. For all hyperparameters (such as batch size and learning rate), please refer to the original paper.
## Evaluation results
| Model | ImageNet top-1 accuracy | # params | URL |
|---------------------------------------|-------------------------|----------|------------------------------------------------------------------|
| PoolFormer-S12 | 77.2 | 12M | https://huggingface.co/sail/poolformer_s12 |
| PoolFormer-S24 | 80.3 | 21M | https://huggingface.co/sail/poolformer_s24 |
| **PoolFormer-S36** | **81.4** | **31M** | **https://huggingface.co/sail/poolformer_s36** |
| PoolFormer-M36 | 82.1 | 56M | https://huggingface.co/sail/poolformer_m36 |
| PoolFormer-M48 | 82.5 | 73M | https://huggingface.co/sail/poolformer_m48 |
### BibTeX entry and citation info
```bibtex
@article{yu2021metaformer,
title={MetaFormer is Actually What You Need for Vision},
author={Yu, Weihao and Luo, Mi and Zhou, Pan and Si, Chenyang and Zhou, Yichen and Wang, Xinchao and Feng, Jiashi and Yan, Shuicheng},
journal={arXiv preprint arXiv:2111.11418},
year={2021}
}
``` |
Aleksandra/distilbert-base-uncased-finetuned-squad | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
tags: salesken
license: apache-2.0
inference: false
---
We have trained a model to evaluate if a paraphrase is a semantic variation to the input query or just a surface level variation. Data augmentation by adding Surface level variations does not add much value to the NLP model training. if the approach to paraphrase generation is "OverGenerate and Rank" , Its important to have a robust model of scoring/ ranking paraphrases. NLG Metrics like bleu ,BleuRT, gleu , Meteor have not proved very effective in scoring paraphrases.
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import pandas as pd
import numpy as np
tokenizer = AutoTokenizer.from_pretrained("salesken/paraphrase_diversity_ranker")
model = AutoModelForSequenceClassification.from_pretrained("salesken/paraphrase_diversity_ranker")
input_query = ["tough challenges make you stronger."]
paraphrases = [
"tough problems make you stronger",
"tough problems will make you stronger",
"tough challenges make you stronger",
"tough challenges will make you a stronger person",
"tough challenges will make you stronger",
"tough tasks make you stronger",
"the tough task makes you stronger",
"tough stuff makes you stronger",
"if tough times make you stronger",
"the tough part makes you stronger",
"tough issues strengthens you",
"tough shit makes you stronger",
"tough tasks force you to be stronger",
"tough challenge is making you stronger",
"tough problems make you have more strength"]
para_pairs=list(pd.MultiIndex.from_product([input_query, paraphrases]))
features = tokenizer(para_pairs, padding=True, truncation=True, return_tensors="pt")
model.eval()
with torch.no_grad():
scores = model(**features).logits
label_mapping = ['surface_level_variation', 'semantic_variation']
labels = [label_mapping[score_max] for score_max in scores.argmax(dim=1)]
sorted_diverse_paraphrases= np.array(para_pairs)[scores[:,1].sort(descending=True).indices].tolist()
print(sorted_diverse_paraphrases)
# to identify the type of paraphrase (surface-level variation or semantic variation)
print("Paraphrase type detection=====", list(zip(para_pairs, labels)))
```
============================================================================
For more robust results, filter out the paraphrases which are not semantically
similar using a model trained on NLI, STS task and then apply the ranker .
```python
from transformers import AutoTokenizer, AutoModelWithLMHead
from transformers import AutoModelForSequenceClassification
from sentence_transformers import SentenceTransformer, util
import torch
import pandas as pd
import numpy as np
tokenizer = AutoTokenizer.from_pretrained("salesken/paraphrase_diversity_ranker")
model = AutoModelForSequenceClassification.from_pretrained("salesken/paraphrase_diversity_ranker")
embedder = SentenceTransformer('stsb-bert-large')
input_query = ["tough challenges make you stronger."]
paraphrases = [
"tough problems make you stronger",
"tough problems will make you stronger",
"tough challenges make you stronger",
"tough challenges will make you a stronger person",
"tough challenges will make you stronger",
"tough tasks make you stronger",
"the tough task makes you stronger",
"tough stuff makes you stronger",
"tough people make you stronger",
"if tough times make you stronger",
"the tough part makes you stronger",
"tough issues strengthens you",
"tough shit makes you stronger",
"tough tasks force you to be stronger",
"tough challenge is making you stronger",
"tough problems make you have more strength"]
corpus_embeddings = embedder.encode(paraphrases, convert_to_tensor=True)
query_embedding = embedder.encode(input_query, convert_to_tensor=True)
cos_scores = util.pytorch_cos_sim(query_embedding, corpus_embeddings)[0]
para_set=np.array(paraphrases)
a=cos_scores.sort(descending=True)
para= para_set[a.indices[a.values>=0.7].cpu()].tolist()
para_pairs=list(pd.MultiIndex.from_product([input_query, para]))
import torch
features = tokenizer(para_pairs, padding=True, truncation=True, return_tensors="pt")
model.eval()
with torch.no_grad():
scores = model(**features).logits
label_mapping = ['surface_level_variation', 'semantic_variation']
labels = [label_mapping[score_max] for score_max in scores.argmax(dim=1)]
sorted_diverse_paraphrases= np.array(para)[scores[:,1].sort(descending=True).indices].tolist()
print("Paraphrases sorted by diversity:=======",sorted_diverse_paraphrases)
# to identify the type of paraphrase (surface-level variation or semantic variation)
print("Paraphrase type detection=====", list(zip(para_pairs, labels)))
``` |
Aleksandra/herbert-base-cased-finetuned-squad | [
"pytorch",
"tensorboard",
"bert",
"question-answering",
"transformers",
"generated_from_trainer",
"license:cc-by-4.0",
"autotrain_compatible"
] | question-answering | {
"architectures": [
"BertForQuestionAnswering"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 8 | null | ---
language: en
thumbnail: https://salesken.ai/assets/images/logo.png
license: apache-2.0
inference: false
widget:
- text: "every moment is a fresh beginning"
tags: salesken
---
Use this model to generate variations to augment the training data used for NLU systems.
```python
from transformers import AutoTokenizer, AutoModelWithLMHead
import torch
if torch.cuda.is_available():
device = torch.device("cuda")
else :
device = "cpu"
tokenizer = AutoTokenizer.from_pretrained("salesken/paraphrase_generation")
model = AutoModelWithLMHead.from_pretrained("salesken/paraphrase_generation").to(device)
input_query="every moment is a fresh beginning"
query= input_query + " ~~ "
input_ids = tokenizer.encode(query.lower(), return_tensors='pt').to(device)
sample_outputs = model.generate(input_ids,
do_sample=True,
num_beams=1,
max_length=128,
temperature=0.9,
top_p= 0.99,
top_k = 30,
num_return_sequences=40)
paraphrases = []
for i in range(len(sample_outputs)):
r = tokenizer.decode(sample_outputs[i], skip_special_tokens=True).split('||')[0]
r = r.split(' ~~ ')[1]
if r not in paraphrases:
paraphrases.append(r)
print(paraphrases)
```
To evaluate if a paraphrase is a semantic variation to the input query or just a surface level variation & rank the generated paraphrases, use the following model:
https://huggingface.co/salesken/paraphrase_diversity_ranker
|
adorkin/xlm-roberta-en-ru-emoji | [
"pytorch",
"safetensors",
"xlm-roberta",
"text-classification",
"en",
"ru",
"dataset:tweet_eval",
"transformers"
] | text-classification | {
"architectures": [
"XLMRobertaForSequenceClassification"
],
"model_type": "xlm-roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 31 | null | ---
tags: salesken
license: apache-2.0
inference: true
datasets: google_wellformed_query
widget:
- text: "what was the reason for everyone for leave the company"
---
This model evaluates the wellformedness (non-fragment, grammatically correct) score of a sentence. Model is case-sensitive and penalises for incorrect case and grammar as well.
['She is presenting a paper tomorrow','she is presenting a paper tomorrow','She present paper today']
[[0.8917],[0.4270],[0.0134]]
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("salesken/query_wellformedness_score")
model = AutoModelForSequenceClassification.from_pretrained("salesken/query_wellformedness_score")
sentences = [' what was the reason for everyone to leave the company ',
' What was the reason behind everyone leaving the company ',
' why was everybody leaving the company ',
' what was the reason to everyone leave the company ',
' what be the reason for everyone to leave the company ',
' what was the reasons for everyone to leave the company ',
' what were the reasons for everyone to leave the company ']
features = tokenizer(sentences, padding=True, truncation=True, return_tensors="pt")
model.eval()
with torch.no_grad():
scores = model(**features).logits
print(scores)
```
|
AlekseyKorshuk/comedy-scripts | [
"pytorch",
"gpt2",
"text-generation",
"transformers"
] | text-generation | {
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": true,
"max_length": 50
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 20 | null | ---
tags: salesken
widget:
- text: "Which name is also used to describe the Amazon rainforest in English? "
---
```python
from transformers import AutoTokenizer, AutoModelWithLMHead
import torch
if torch.cuda.is_available():
device = torch.device("cuda")
else :
device = "cpu"
tokenizer = AutoTokenizer.from_pretrained("salesken/text_generate")
model = AutoModelWithLMHead.from_pretrained("salesken/text_generate").to(device)
input_query="tough challenges make you stronger. "
input_ids = tokenizer.encode(input_query.lower(), return_tensors='pt').to(device)
sample_outputs = model.generate(input_ids,
do_sample=True,
num_beams=1,
max_length=1024,
temperature=0.99,
top_k = 10,
num_return_sequences=1)
for i in range(len(sample_outputs)):
print(tokenizer.decode(sample_outputs[i], skip_special_tokens=True))
``` |
AlekseyKorshuk/horror-scripts | [
"pytorch",
"gpt2",
"text-generation",
"transformers"
] | text-generation | {
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": true,
"max_length": 50
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 19 | null | ---
license: apache-2.0
language:
- hi
tags:
- translation
- salesken
- hi
- opus-mt
---
opus-mt model finetuned on ai4bhart Hindi-English parallel corpora (SAMANANTAR)
source-language: Hindi
target-language: English
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("salesken/translation-hi-en")
model = AutoModelForSeq2SeqLM.from_pretrained("salesken/translation-hi-en")
hin_snippet = "कोविड के कारण हमने अपने ऋण ब्याज को कम कर दिया है"
inputs = tokenizer.encode(
hin_snippet, return_tensors="pt",padding=True,max_length=512,truncation=True)
outputs = model.generate(
inputs, max_length=128, num_beams=None, early_stopping=True)
translated = tokenizer.decode(outputs[0]).replace('<pad>',"").strip().lower()
print(translated)
# due to covid, we have reduced our debt interest
``` |
AlekseyKulnevich/Pegasus-HeaderGeneration | [
"pytorch",
"pegasus",
"text2text-generation",
"transformers",
"autotrain_compatible"
] | text2text-generation | {
"architectures": [
"PegasusForConditionalGeneration"
],
"model_type": "pegasus",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 8 | null | ---
datasets:
- mnli
- xnli
tags:
- sentence-similarity
- transformers
- text-classification
- zero-shot-classification
- salesken
- hindi
- cross-lingual
inference: false
---
# XLM-R Base
A multilingual model is pre-trained on text coming from a mix of languages. We will look at a multilingual model called XLM-R from Facebook also called as Cross Lingual Model - Roberta. Unlike BERT which was pre-trained on English Wikipedia and BookCorpus, XLM-R was pre-trained on Wikipedia and Common Crawl data from 100 different languages. A single model trained on 100 different languages.
* So, there is a single shared vocabulary with 250K tokens to cover all 100 languages.
* There is no special marker which suggests which language it is.
* It wasn't trained with parallel data (i.e. same sentence in multiple languages)
# Cross Lingual Transfer (Zero-shot transfer)
Say you are building a classifier which will classify Hindi comments toxic or non-toxic. But say you have a training dataset in English of 225 K labeled comments called "Wikipedia Toxic Comments". The Cross Lingual Transfer of XLM-R will let you fine-tune XLM-R on Wikipedia Toxic Comments dataset in English, and then apply it to Hindi comments. So, XLM-R is able to take it's task specific knowledge that it learned in English and apply it on Hindi, even though we never showed it any Hindi exmaples. It's concept of transfer learning applied from one language to another which is called Cross Lingual Transfer. The same could be done on any other low-resource languages
We will see that training XLM-R purely on ~400K English samples acutally yields better results than fine-tuning a monolingual Hindi model on a much smaller Hindi dataset. This is also referred to as Zero-Shot Learning or Cross-Lingual Transfer
# Our Approach -
We will use MNLI that provides us with a large number of English training examples to fine-tune XLM-R on the general task of NLI. XNLI will provide us with a small number of NLI test examples in different languages for us it will be Hindi. MNLI (Multi-genre NLI) has 392,000 training examples and 20,000 development examples and 20,000 test examples. On the other hand XNLI is a small subset of examples from MNLI dataset which have been human-translated to 14 different languages and yes Hindi is a part of it. For each language we have 5,000 test set sentence pairs and 2,500 development set sentence pairs
# Fine-tuning Hyperparameters -
learning rate : 5e-6 with linear learning rate scheduling over total steps
epochs = 2
batch_size = 32
GPU : Tesla T4
# Using this model
This model can be used using Huggingface Transformers. I have created a pipeline for a sentence pair classification. Hope it will be useful.
```python
!pip3 install transformers
import transformers
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("salesken/xlm-roberta-base-finetuned-mnli-cross-lingual-transfer")
model = AutoModelForSequenceClassification.from_pretrained("salesken/xlm-roberta-base-finetuned-mnli-cross-lingual-transfer")
device = torch.device('cuda')
print('GPU: ', torch.cuda.get_device_name(0))
model.to(device)
# Here I am giving the sentence pairs and also the ground truth values (1 : Similar, 0 : NotSimilar)
# we have purposely used Hindi-Hindi , Hindi-English, Transliterated Hindi-Engish, Kannada and Spanish and also code-switching of languages
# You can try your own pairs and languages
u_premise = ['क्या आपका बेटा गणित में रूचि रखता है',
'क्या आपका बेटा गणित में रूचि रखता है',
'क्या आपका बेटा गणित में रूचि रखता है',
'मैं त्योहार के दौरान घर जा रहा हूँ',
'क्या आपका बेटा गणित में रूचि रखता है',
'hum ek cross lingual model banane ka soch rahe hai',
'we are planning to build a cross-lingual language model',
'Hi. A very good morning to all of you. Lets get started. ',
'शुभ प्रभात',
'how are you doing today sir ?',
'how are you doing today sir ?',
'Argentina and Brazil will play Copa America finals this weekend',
'I want to visit Spain and Portugal next year'
]
u_hypothesis = ['क्या आपकी बेटी को विज्ञान में दिलचस्पी है',
'is your daughther interested in science',
'is your son interested in stem subjects',
'इस साल मैं त्योहार के दौरान घर नहीं जाऊंगा',
'इस साल मैं त्योहार के दौरान घर नहीं जाऊंगा',
'हम एक क्रॉस-लिंगुअल लैंग्वेज मॉडल बनाने की योजना बना रहे हैं',
'hum ek क्रॉस-लिंगुअल model bana rahe hai',
'शुभ प्रभात',
'subh prabhat to all of you',
'ಇಂದು ನೀವು ಹೇಗಿದ್ದೀರಿ ಸರ್?',
'ನನ್ನ ಸ್ನಾತಕೋತ್ತರರಿಗಾಗಿ ನಾನು ಯಂತ್ರ ಕಲಿಕೆ ಮತ್ತು ಡೇಟಾ ವಿಜ್ಞಾನವನ್ನು ಮಾಡುತ್ತಿದ್ದೇನೆ',
'Argentina y Brasil jugarán la final de la Copa América este fin de semana',
'Puedes ver la aurora boreal desde Noruega']
ground_truth = [1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0]
from torch.utils.data import TensorDataset, DataLoader
import numpy as np
import textwrap
import pandas as pd
labels_ar = []
input_ids_ar = []
attn_masks_ar = []
max_len = 128
batch_size = 32
label_names = ['entailment', 'neutral', 'contradiction']
for u_prem, u_hyp in zip(u_premise, u_hypothesis):
encoded_dict = tokenizer.encode_plus(u_prem, u_hyp,
max_length=max_len,
padding='max_length',
truncation=True,
return_tensors='pt')
# Add this example to our lists.
input_ids_ar.append(encoded_dict['input_ids'])
attn_masks_ar.append(encoded_dict['attention_mask'])
# Convert each Python list of Tensors into a 2D Tensor matrix.
input_ids_ar = torch.cat(input_ids_ar, dim=0)
attn_masks_ar = torch.cat(attn_masks_ar, dim=0)
# Construct a TensorDataset from the encoded examples.
prediction_dataset = TensorDataset(input_ids_ar, attn_masks_ar)
# And a dataloader for handling batching.
prediction_dataloader = DataLoader(prediction_dataset, batch_size=batch_size)
# Put model in evaluation mode
model.eval()
# Tracking variables
predictions , true_labels = [], []
count = 0
# Predict
for batch in prediction_dataloader:
batch = tuple(t.to(device) for t in batch)
b_input_ids, b_input_mask = batch
with torch.no_grad():
# Forward pass, calculate logit predictions
outputs = model(b_input_ids,
attention_mask=b_input_mask)
logits = outputs[0]
# Move logits to CPU
logits = logits.detach().cpu().numpy()
# Store predictions and true labels
predictions.append(logits)
# Combine the results across all batches.
flat_predictions = np.concatenate(predictions, axis=0)
# For each sample, pick the label (0, 1, or 2) with the highest score.
predicted_labels = np.argmax(flat_predictions, axis=1).flatten()
wrapper = textwrap.TextWrapper(width = 80, initial_indent=' ',subsequent_indent=' ')
def softmax(logits):
return np.exp(logits) / np.sum(np.exp(logits))
finalOut = []
for sentA, sentB, pred_logits, grnd_truth in zip(u_premise, u_hypothesis, flat_predictions, ground_truth):
probScore = softmax(pred_logits)
maxScore = {'idx': 0, 'score': 0}
for idx, score in enumerate(probScore):
if score > maxScore['score']:
maxScore['score'] = score
maxScore['idx'] = idx
if maxScore['score'] > 0.4:
if maxScore['idx'] == 0:
label = 'Similar'
else:
label = 'NotSimilar'
finalOut.append((sentA, sentB, label, grnd_truth, maxScore['score']))
pd.set_option("display.max_colwidth", -1)
pd.DataFrame(finalOut, columns = ['sentence-1', 'sentence-2', 'semantic_matching', 'ground_truth', 'probability_score'])
```
|
Alireza1044/albert-base-v2-wnli | [
"pytorch",
"albert",
"text-classification",
"en",
"dataset:glue",
"transformers",
"generated_from_trainer",
"license:apache-2.0"
] | text-classification | {
"architectures": [
"AlbertForSequenceClassification"
],
"model_type": "albert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 164 | null | ---
language:
- eo
license: apache-2.0
tags:
- automatic-speech-recognition
- common_voice
- eo
- generated_from_trainer
- hf-asr-leaderboard
- robust-speech-event
datasets:
- common_voice
model-index:
- name: wav2vec2-xls-r-300m-eo
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 7
type: mozilla-foundation/common_voice_7_0
args: eo
metrics:
- name: Test WER
type: wer
value: 34.72
- name: Test CER
type: cer
value: 7.54
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# wav2vec2-xls-r-300m-eo
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the COMMON_VOICE - EO dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2584
- Wer: 0.3114
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 3.1701 | 0.8 | 500 | 2.8105 | 1.0 |
| 1.9143 | 1.6 | 1000 | 0.5977 | 0.7002 |
| 1.1259 | 2.4 | 1500 | 0.5063 | 0.6157 |
| 0.9732 | 3.2 | 2000 | 0.4264 | 0.5673 |
| 0.8983 | 4.0 | 2500 | 0.4249 | 0.4902 |
| 0.8507 | 4.8 | 3000 | 0.3811 | 0.4536 |
| 0.8064 | 5.6 | 3500 | 0.3643 | 0.4467 |
| 0.7866 | 6.4 | 4000 | 0.3600 | 0.4453 |
| 0.7773 | 7.2 | 4500 | 0.3724 | 0.4470 |
| 0.747 | 8.0 | 5000 | 0.3501 | 0.4189 |
| 0.7279 | 8.8 | 5500 | 0.3500 | 0.4261 |
| 0.7153 | 9.6 | 6000 | 0.3328 | 0.3966 |
| 0.7 | 10.4 | 6500 | 0.3314 | 0.3869 |
| 0.6784 | 11.2 | 7000 | 0.3396 | 0.4051 |
| 0.6582 | 12.0 | 7500 | 0.3236 | 0.3899 |
| 0.6478 | 12.8 | 8000 | 0.3263 | 0.3832 |
| 0.6277 | 13.6 | 8500 | 0.3139 | 0.3769 |
| 0.6053 | 14.4 | 9000 | 0.2955 | 0.3536 |
| 0.5777 | 15.2 | 9500 | 0.2793 | 0.3413 |
| 0.5631 | 16.0 | 10000 | 0.2789 | 0.3353 |
| 0.5446 | 16.8 | 10500 | 0.2709 | 0.3264 |
| 0.528 | 17.6 | 11000 | 0.2693 | 0.3234 |
| 0.5169 | 18.4 | 11500 | 0.2656 | 0.3193 |
| 0.5041 | 19.2 | 12000 | 0.2575 | 0.3102 |
| 0.4971 | 20.0 | 12500 | 0.2584 | 0.3114 |
### Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu102
- Datasets 1.18.2.dev0
- Tokenizers 0.11.0
#### Evaluation Commands
1. To evaluate on `mozilla-foundation/common_voice_7_0` with split `test`
```bash
python eval.py --model_id samitizerxu/wav2vec2-xls-r-300m-eo --dataset mozilla-foundation/common_voice_7_0 --config eo --split test
``` |
Amit29/t5-small-finetuned-xsum | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | A Named Entity Recognition model for clinical entities (`problem`, `treatment`, `test`)
The model has been trained on the [i2b2 (now n2c2) dataset](https://n2c2.dbmi.hms.harvard.edu) for the 2010 - Relations task. Please visit the n2c2 site to request access to the dataset. |
AmitT/test | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | A Named Entity Recognition model for medication entities (`medication name`, `dosage`, `duration`, `frequency`, `reason`).
The model has been trained on the i2b2 (now n2c2) dataset for the 2009 - Medication task. Please visit the n2c2 site to request access to the dataset. |
AnonymousSub/AR_rule_based_roberta_twostagetriplet_hier_epochs_1_shard_10 | [
"pytorch",
"roberta",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"RobertaModel"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 6 | null | ---
language:
- en
thumbnail:
tags:
- conversational
metrics:
- perplexity
---
## DialoGPT model fine-tuned using Amazon's Topical Chat Dataset
This model is fine-tuned from the original [DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium).
This model was fine-tuned on a subset of messages from [Amazon's Topical Chat dataset](https://www.kaggle.com/arnavsharmaas/chatbot-dataset-topical-chat) (due to processing limitations, I restricted my training data to 50,000 observations.
The dataset spands 8 broad topics and contains conversation partner who do not have defined roles. It was created with the goal of [aiding in the effort to build a socialbot that can have deep, engaging open-domain conversations with humans](https://m.media-amazon.com/images/G/01/amazon.jobs/3079_Paper._CB1565131710_.pdf).
The eight broad topics are:
- fashion
- politics
- books
- sports
- general entertainment
- music
- science and technology
- movies
<br><br>
<b>Sample dialogue:</b>
|Role | Response |
|---------|--------|
|User: | What kind of movies do you like? |
| Bot: | I like marvel movies like iron man |
|User: | Do you like horror films? |
| Bot: | Yea, I like the horror films that have macabre and supernatural themes the most |
|User: | Interesting. |
| Bot: | If you watch a horror movie before you view abstract art, you will enjoy the art more |
|User: | Speaking from experience? |
| Bot: | Yes, I've seen many horror movies where the characters were quite evil and supernatural. |
## Using the model
Example code for trying out the model (taken directly from the [DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium) model card):
```python
from transformers import AutoModelWithLMHead, AutoTokenizer
import torch
tokenizer = AutoTokenizer.from_pretrained("satkinson/DialoGPT-small-marvin")
model = AutoModelWithLMHead.from_pretrained("satkinson/DialoGPT-small-marvin")
# Let's chat for 5 lines
for step in range(5):
# encode the new user input, add the eos_token and return a tensor in Pytorch
new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
# append the new user input tokens to the chat history
bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
# generated a response while limiting the total chat history to 1000 tokens,
chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
# pretty print last ouput tokens from bot
print("DialoGPT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
``` |
AnonymousSub/SR_rule_based_roberta_hier_triplet_epochs_1_shard_10 | [
"pytorch",
"roberta",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"RobertaModel"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 6 | null | ---
language:
- ru
- en
tags:
- PyTorch
thumbnail: "https://github.com/sberbank-ai/Real-ESRGAN"
---
# Real-ESRGAN
PyTorch implementation of a Real-ESRGAN model trained on custom dataset. This model shows better results on faces compared to the original version. It is also easier to integrate this model into your projects.
Real-ESRGAN is an upgraded ESRGAN trained with pure synthetic data is capable of enhancing details while removing annoying artifacts for common real-world images.
- [Paper](https://arxiv.org/abs/2107.10833)
- [Original implementation](https://github.com/xinntao/Real-ESRGAN)
- [Our github](https://github.com/sberbank-ai/Real-ESRGAN)
## Usage
Code for using model you can obtain in our [repo](https://github.com/sberbank-ai/Real-ESRGAN).
```python
import torch
from PIL import Image
import numpy as np
from RealESRGAN import RealESRGAN
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = RealESRGAN(device, scale=4)
model.load_weights('weights/RealESRGAN_x4.pth', download=True)
path_to_image = 'inputs/lr_image.png'
image = Image.open(path_to_image).convert('RGB')
sr_image = model.predict(image)
sr_image.save('results/sr_image.png')
``` |
AnonymousSub/SR_rule_based_roberta_hier_triplet_epochs_1_shard_1_wikiqa_copy | [
"pytorch",
"roberta",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"RobertaModel"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 2 | null | ---
tags:
- RUDOLPH
- text-image
- image-text
- decoder
datasets:
- sberquad
---
# RUDOLPH-350M (Small)
RUDOLPH: One Hyper-Tasking Transformer Сan be Сreative as DALL-E and GPT-3 and Smart as CLIP
<img src="https://raw.githubusercontent.com/sberbank-ai/ru-dolph/master/pics/RUDOLPH.png" width=60% border="2"/>
Model was trained by [Sber AI](https://github.com/ai-forever) team.
# Model Description
**RU**ssian **D**ecoder **O**n **L**anguage **P**icture **H**yper-tasking (**RUDOLPH**) **350M** is a fast and light text-image-text transformer designed for a quick and easy fine-tuning for a range of tasks: from generating images by text description and image classification to visual question answering and more. This model demonstrates the power of Hyper-tasking Transformers.
*Hyper-tasking model is a generalized multi-tasking model, i.e., the model that can solve almost all tasks within supported modalities, mandatory including mutual pairwise translations between modalities (two modalities in case of RUDOLPH: images and Russian texts).*
* Tasks: ` text2image generation, self reranking, text ranking, image ranking, image2text generation, zero-shot image classification, text2text generation, and so on`
* Language: ` Russian`
* Type: ` decoder`
* Num Parameters: ` 350M`
* Training Data Volume: `141 million text-image pairs, 7.6 million text paragraphs`
# Details of architecture
<img src=https://raw.githubusercontent.com/ai-forever/ru-dolph/master/pics/scheme-rudolph_350m.jpg height="20" border="2"/>
The maximum sequence length that this model may be used with depends on the modality and stands for 64 - 256 - 64 for the left text tokens, image tokens, and right text tokens, respectively.
RUDOLPH 350M is a Transformer-based decoder model with the following parameters:
* num\_layers (24) — Number of hidden layers in the Transformer decoder.
* hidden\_size (1024) — Dimensionality of the hidden layers.
* num\_attention\_heads (16) — Number of attention heads for each attention layer.
# Sparse Attention Masks
The primary proposed method is to modify the sparse transformer's attention mask to better control modalities. It allows us to calculate the transitions of modalities in both directions, unlike another similar work DALL-E Transformer, which used only one direction, "text to image". The proposed "image to right text" direction is achieved by extension sparse attention mask to the right for auto-repressively text generation with both image and left text condition.
<img src="https://raw.githubusercontent.com/sberbank-ai/ru-dolph/master/pics/attention_masks_350m.png" height="40" border="2"/>
# Authors
+ Alex Shonenkov: [Github](https://github.com/shonenkov), [Kaggle GM](https://www.kaggle.com/shonenkov)
+ Michael Konstantinov: [Mishin Learning](https://t.me/mishin_learning), [Transformer Community](https://transformer.community/)
|
AnonymousSub/SR_rule_based_roberta_twostagequadruplet_hier_epochs_1_shard_10 | [
"pytorch",
"roberta",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"RobertaModel"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 4 | null | ---
language:
- ru
tags:
- PyTorch
- Transformers
thumbnail: "https://github.com/sberbank-ai/model-zoo"
---
# ruT5-large
Model was trained by [SberDevices](https://sberdevices.ru/).
* Task: `text2text generation`
* Type: `encoder-decoder`
* Tokenizer: `bpe`
* Dict size: `32 101 `
* Num Parameters: `737 M`
* Training Data Volume `300 GB`
# Authors
+ NLP core team RnD [Telegram channel](https://t.me/nlpcoreteam):
+ Dmitry Zmitrovich |
AnonymousSub/SR_rule_based_roberta_twostagetriplet_epochs_1_shard_1 | [
"pytorch",
"roberta",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"RobertaModel"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 8 | null | # ruclip-vit-base-patch16-224
**RuCLIP** (**Ru**ssian **C**ontrastive **L**anguage–**I**mage **P**retraining) is a multimodal model
for obtaining images and text similarities and rearranging captions and pictures.
RuCLIP builds on a large body of work on zero-shot transfer, computer vision, natural language processing and
multimodal learning.
Model was trained by [Sber AI](https://github.com/sberbank-ai) and [SberDevices](https://sberdevices.ru/) teams.
* Task: `text ranking`; `image ranking`; `zero-shot image classification`;
* Type: `encoder`
* Num Parameters: `150M`
* Training Data Volume: `240 million text-image pairs`
* Language: `Russian`
* Context Length: `77`
* Transformer Layers: `12`
* Transformer Width: `512`
* Transformer Heads: `8`
* Image Size: `224`
* Vision Layers: `12`
* Vision Width: `768`
* Vision Patch Size: `16`
## Usage [Github](https://github.com/sberbank-ai/ru-clip)
```
pip install ruclip
```
```python
clip, processor = ruclip.load("ruclip-vit-base-patch16-224", device="cuda")
```
## Performance
We have evaluated the performance on the following datasets:
| Dataset | Metric Name | Metric Result |
|:--------------|:---------------|:--------------------|
| Food101 | acc | 0.552 |
| CIFAR10 | acc | 0.810 |
| CIFAR100 | acc | 0.496 |
| Birdsnap | acc | 0.117 |
| SUN397 | acc | 0.462 |
| Stanford Cars | acc | 0.487 |
| DTD | acc | 0.401 |
| MNIST | acc | 0.464 |
| STL10 | acc | 0.932 |
| PCam | acc | 0.505 |
| CLEVR | acc | 0.128 |
| Rendered SST2 | acc | 0.527 |
| ImageNet | acc | 0.401 |
| FGVC Aircraft | mean-per-class | 0.043 |
| Oxford Pets | mean-per-class | 0.595 |
| Caltech101 | mean-per-class | 0.775 |
| Flowers102 | mean-per-class | 0.388 |
| HatefulMemes | roc-auc | 0.516 |
# Authors
+ Alex Shonenkov: [Github](https://github.com/shonenkov), [Kaggle GM](https://www.kaggle.com/shonenkov)
+ Daniil Chesakov: [Github](https://github.com/Danyache)
+ Denis Dimitrov: [Github](https://github.com/denndimitrov)
+ Igor Pavlov: [Github](https://github.com/boomb0om)
|
AnonymousSub/SR_rule_based_roberta_twostagetriplet_hier_epochs_1_shard_1 | [
"pytorch",
"roberta",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"RobertaModel"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 4 | null | # ruclip-vit-base-patch32-224
**RuCLIP** (**Ru**ssian **C**ontrastive **L**anguage–**I**mage **P**retraining) is a multimodal model
for obtaining images and text similarities and rearranging captions and pictures.
RuCLIP builds on a large body of work on zero-shot transfer, computer vision, natural language processing and
multimodal learning.
Model was trained by [Sber AI](https://github.com/sberbank-ai) and [SberDevices](https://sberdevices.ru/) teams.
* Task: `text ranking`; `image ranking`; `zero-shot image classification`;
* Type: `encoder`
* Num Parameters: `150M`
* Training Data Volume: `240 million text-image pairs`
* Language: `Russian`
* Context Length: `77`
* Transformer Layers: `12`
* Transformer Width: `512`
* Transformer Heads: `8`
* Image Size: `224`
* Vision Layers: `12`
* Vision Width: `768`
* Vision Patch Size: `32`
## Usage [Github](https://github.com/sberbank-ai/ru-clip)
```
pip install ruclip
```
```python
clip, processor = ruclip.load("ruclip-vit-base-patch32-224", device="cuda")
```
## Performance
We have evaluated the performance on the following datasets:
| Dataset | Metric Name | Metric Result |
|:--------------|:---------------|:--------------------|
| Food101 | acc | 0.505 |
| CIFAR10 | acc | 0.818 |
| CIFAR100 | acc | 0.504 |
| Birdsnap | acc | 0.115 |
| SUN397 | acc | 0.452 |
| Stanford Cars | acc | 0.433 |
| DTD | acc | 0.380 |
| MNIST | acc | 0.447 |
| STL10 | acc | 0.932 |
| PCam | acc | 0.501 |
| CLEVR | acc | 0.148 |
| Rendered SST2 | acc | 0.489 |
| ImageNet | acc | 0.375 |
| FGVC Aircraft | mean-per-class | 0.033 |
| Oxford Pets | mean-per-class | 0.560 |
| Caltech101 | mean-per-class | 0.786 |
| Flowers102 | mean-per-class | 0.401 |
| HatefulMemes | roc-auc | 0.564 |
# Authors
+ Alex Shonenkov: [Github](https://github.com/shonenkov), [Kaggle GM](https://www.kaggle.com/shonenkov)
+ Daniil Chesakov: [Github](https://github.com/Danyache)
+ Denis Dimitrov: [Github](https://github.com/denndimitrov)
+ Igor Pavlov: [Github](https://github.com/boomb0om)
|
AnonymousSub/SR_rule_based_twostagetriplet_hier_epochs_1_shard_1 | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 2 | 2021-11-01T16:16:29Z | ---
language:
- ru
- en
pipeline_tag: text-to-image
tags:
- PyTorch
- Transformers
thumbnail: "https://github.com/sberbank-ai/ru-dalle"
---
# ruDALL-E Malevich (XL)
## Generate images from text
<img style="text-align:center; display:block;" src="https://huggingface.co/sberbank-ai/rudalle-Malevich/resolve/main/dalle-malevich.jpg" width="200">
"Avocado painting in the style of Malevich"
* [Technical Report (Russian)](https://habr.com/ru/company/sberbank/blog/586926)
* [Demo](https://rudalle.ru)
Model was trained by [Sber AI](https://github.com/sberbank-ai) and [SberDevices](https://sberdevices.ru/) teams.
* Task: `text2image generation`
* Type: `encoder-decoder`
* Num Parameters: `1.3 B`
* Training Data Volume: `120 million text-image pairs`
### Model Description
This is a 1.3 billion parameter model for Russian, recreating OpenAI's [DALL·E](https://openai.com/blog/dall-e/), a model capable of generating arbitrary images from a text prompt that describes the desired result.
The generation pipeline includes ruDALL-E, ruCLIP for ranging results, and a superresolution model.
You can use automatic translation into Russian to create desired images with ruDALL-E.
### How to Use
The easiest way to get familiar with the code and the models is to follow the inference notebook we provide in our [github repo](https://github.com/sberbank-ai/ru-dalle).
## Motivation
One might say that “investigate, master, and train” is our engineering motto. Well, we caught the scent, and today we can say that we created from scratch a complete pipeline for generating images from descriptive textual input written in Russian.
Teams at SberAI, SberDevices, Samara University, AIRI and SberCloud all actively contributed.
We trained two versions of the model, each a different size, and named them after Russia’s great abstractionists: Vasily Kandinsky and Kazimir Malevich.
* ruDALL-E Kandinsky (XXL), with 12 billion parameters
* ruDALL-E Malevich (XL), having 1.3 billion parameters
Some of our models are already freely available:
* ruDALL-E Malevich (XL) [[GitHub](https://github.com/sberbank-ai/ru-dalle), [HuggingFace](https://huggingface.co/sberbank-ai/rudalle-Malevich)]
* Sber VQ-GAN [[GitHub](https://github.com/sberbank-ai/sber-vq-gan), [HuggingFace](https://huggingface.co/sberbank-ai/Sber-VQGAN)]
* ruCLIP Small [[GitHub](https://github.com/sberbank-ai/ru-clip), [HuggingFace](https://huggingface.co/sberbank-ai/ru-clip)]
* Super Resolution (Real ESRGAN) [[GitHub](https://github.com/sberbank-ai/Real-ESRGAN), [HuggingFace](https://huggingface.co/sberbank-ai/Real-ESRGAN)]
The latter two models are included in the pipeline for generating images from text (as you’ll see later on).
The models ruDALL-E Malevich (XL), ruDALL-E Kandinsky (XXL), ruCLIP Small, ruCLIP Large, and Super Resolution (Real ESRGAN) will also soon be available on [DataHub](https://mlspace.aicloud.sbercloud.ru/mlspace/datahub).
Training the ruDALL-E neural networks on the Christofari cluster has become the largest calculation task in Russia:
* ruDALL-E Kandinsky (XXL) was trained for 37 days on the 512 GPU TESLA V100, and then also for 11 more days on the 128 GPU TESLA V100, for a total of 20,352 GPU-days;
* ruDALL-E Malevich (XL) was trained for 8 days on the 128 GPU TESLA V100, and then also for 15 more days on the 192 GPU TESLA V100, for a total of 3,904 GPU-days.
Accordingly, training for both models totalled 24,256 GPU-days.
## Model capabilities
The long term goal of this research is the creation of multimodal neural networks. They will be able to pull on concepts from a variety of mediums---from text and visuals at first---in order to better understand the world as a whole.
Image generation might seem like the wrong rabbit hole in our century of big data and search engines. But it actually addresses two important requirements that search is currently unable to cope with:
1. Being able to describe in writing exactly what you’re looking for and getting a completely new image created personally for you.
2. Being able to create at any time as many license-free illustrations as you could possibly want
"Grand Canyon"
<img style="text-align:center; display:block;" src="https://habrastorage.org/webt/kb/sv/ih/kbsvihfsmz3fx5mvitii0seimi0.jpeg" width="800">
"Salvador Dali picture"
<img style="text-align:center; display:block;" src="https://habrastorage.org/webt/r8/nl/oi/r8nloiq-l8j2ckg6pzh2pufsklm.jpeg" width="800">
"An eagle sits in a tree, looking to the side"
<img style="text-align:center; display:block;" src="https://habrastorage.org/r/w1560/getpro/habr/upload_files/10a/19c/fa2/10a19cfa2cc84aa7c8b99820890e908d.png" width="800">
"Elegant living room with green stuffed chairs"
<img style="text-align:center; display:block;" src="https://habrastorage.org/r/w1560/getpro/habr/upload_files/6fe/e69/d7c/6fee69d7c392239d587725799e0e41e4.png" width="800">
“Raccoon with a gun”
<img style="text-align:center; display:block;" src="https://habrastorage.org/r/w1560/getpro/habr/upload_files/3bb/1b8/7c4/3bb1b87c45bf9305cd342ae9900ac245.png" width="800">
“Pretty lake at sunset”
<img style="text-align:center; display:block;" src="https://habrastorage.org/r/w1560/getpro/habr/upload_files/241/781/fe9/241781fe99da510d4d5fea03af635e88.png" width="800">
|
AnonymousSub/SR_specter | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 5 | null | ---
language:
- ru
tags:
- PyTorch
- Transformers
thumbnail: "https://github.com/sberbank-ai/ru-gpts"
---
# rugpt2large
Model was trained with sequence length 1024 using transformers by [SberDevices](https://sberdevices.ru/) team on 170Gb data on 64 GPUs 3 weeks.
|
AnonymousSub/cline-emanuals-s10-SR | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | For details, please refer to the following links.
Github repo: https://github.com/amazon-research/SC2QA-DRIL
Paper: [Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning](https://arxiv.org/pdf/2109.04689.pdf) |
AnonymousSub/cline-papers-roberta-0.585 | [
"pytorch",
"roberta",
"transformers"
] | null | {
"architectures": [
"LecbertForPreTraining"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 1 | null | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: Prototype_training
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Prototype_training
This model is a fine-tuned version of [scasutt/Prototype_training](https://huggingface.co/scasutt/Prototype_training) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3719
- Wer: 0.4626
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.3853 | 1.47 | 100 | 0.3719 | 0.4626 |
| 0.3867 | 2.94 | 200 | 0.3719 | 0.4626 |
### Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3
|
AnonymousSub/cline-s10-AR | [
"pytorch",
"roberta",
"text-classification",
"transformers"
] | text-classification | {
"architectures": [
"RobertaForSequenceClassification"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 31 | null | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: Prototype_training_large_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Prototype_training_large_model
This model is a fine-tuned version of [scasutt/Prototype_training_large_model](https://huggingface.co/scasutt/Prototype_training_large_model) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2585
- Wer: 1.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---:|
| 3.0545 | 1.47 | 100 | 3.2604 | 1.0 |
| 3.0413 | 2.93 | 200 | 3.2585 | 1.0 |
### Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3
|
AnonymousSub/consert-s10-AR | [
"pytorch",
"bert",
"text-classification",
"transformers"
] | text-classification | {
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 31 | null | ---
language: en
license: apache-2.0
---
## ELECTRA-small-cased
This is a cased version of `google/electra-small-discriminator`, trained on the
[OpenWebText corpus](https://skylion007.github.io/OpenWebTextCorpus/).
Uses the same tokenizer and vocab from `bert-base-cased`
|
AnonymousSub/declutr-emanuals-s10-AR | [
"pytorch",
"roberta",
"text-classification",
"transformers"
] | text-classification | {
"architectures": [
"RobertaForSequenceClassification"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 29 | null | ---
tags:
- generated_from_trainer
datasets:
- jnlpba
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: biobert-base-cased-v1.2-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: jnlpba
type: jnlpba
args: jnlpba
metrics:
- name: Precision
type: precision
value: 0.7150627220423177
- name: Recall
type: recall
value: 0.8300729927007299
- name: F1
type: f1
value: 0.7682875335686659
- name: Accuracy
type: accuracy
value: 0.90497239665345
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# biobert-base-cased-v1.2-finetuned-ner
This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the jnlpba dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3655
- Precision: 0.7151
- Recall: 0.8301
- F1: 0.7683
- Accuracy: 0.9050
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.257 | 1.0 | 1160 | 0.2889 | 0.7091 | 0.8222 | 0.7615 | 0.9021 |
| 0.1962 | 2.0 | 2320 | 0.3009 | 0.7154 | 0.8259 | 0.7667 | 0.9048 |
| 0.158 | 3.0 | 3480 | 0.3214 | 0.7098 | 0.8228 | 0.7621 | 0.9031 |
| 0.131 | 4.0 | 4640 | 0.3385 | 0.7174 | 0.8292 | 0.7692 | 0.9055 |
| 0.1081 | 5.0 | 5800 | 0.3655 | 0.7151 | 0.8301 | 0.7683 | 0.9050 |
### Framework versions
- Transformers 4.11.3
- Pytorch 1.9.1+cu102
- Datasets 1.13.2
- Tokenizers 0.10.3
|
AnonymousSub/rule_based_hier_quadruplet_epochs_1_shard_10 | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 4 | null | ---
language:
- ta
- en
- multilingual
license: apache-2.0
tags:
- Text Classification
datasets:
- dravidiancodemixed
metrics:
- f1
- accuracy
---
Model card Coming soon
|
AnonymousSub/rule_based_hier_triplet_epochs_1_shard_1_wikiqa_copy | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 1 | null | ---
language: "en"
tags:
- dpr
- dense-passage-retrieval
- knowledge-distillation
datasets:
- ms_marco
---
# Margin-MSE Trained ColBERT
We provide a retrieval trained DistilBert-based ColBERT model (https://arxiv.org/pdf/2004.12832.pdf). Our model is trained with Margin-MSE using a 3 teacher BERT_Cat (concatenated BERT scoring) ensemble on MSMARCO-Passage.
This instance can be used to **re-rank a candidate set** or **directly for a vector index based dense retrieval**. The architecure is a 6-layer DistilBERT, with an additional single linear layer at the end.
If you want to know more about our simple, yet effective knowledge distillation method for efficient information retrieval models for a variety of student architectures that is used for this model instance check out our paper: https://arxiv.org/abs/2010.02666 🎉
For more information, training data, source code, and a minimal usage example please visit: https://github.com/sebastian-hofstaetter/neural-ranking-kd
## Configuration
- fp16 trained, so fp16 inference shouldn't be a problem
- We use no compression: 768 dim output vectors (better suited for re-ranking, or storage for smaller collections, MSMARCO gets to ~1TB vector storage with fp16 ... ups)
- Query [MASK] augmention = 8x regardless of batch-size (needs to be added before the model, see the usage example in GitHub repo for more)
## Model Code
````python
from transformers import AutoTokenizer,AutoModel, PreTrainedModel,PretrainedConfig
from typing import Dict
import torch
class ColBERTConfig(PretrainedConfig):
model_type = "ColBERT"
bert_model: str
compression_dim: int = 768
dropout: float = 0.0
return_vecs: bool = False
trainable: bool = True
class ColBERT(PreTrainedModel):
"""
ColBERT model from: https://arxiv.org/pdf/2004.12832.pdf
We use a dot-product instead of cosine per term (slightly better)
"""
config_class = ColBERTConfig
base_model_prefix = "bert_model"
def __init__(self,
cfg) -> None:
super().__init__(cfg)
self.bert_model = AutoModel.from_pretrained(cfg.bert_model)
for p in self.bert_model.parameters():
p.requires_grad = cfg.trainable
self.compressor = torch.nn.Linear(self.bert_model.config.hidden_size, cfg.compression_dim)
def forward(self,
query: Dict[str, torch.LongTensor],
document: Dict[str, torch.LongTensor]):
query_vecs = self.forward_representation(query)
document_vecs = self.forward_representation(document)
score = self.forward_aggregation(query_vecs,document_vecs,query["attention_mask"],document["attention_mask"])
return score
def forward_representation(self,
tokens,
sequence_type=None) -> torch.Tensor:
vecs = self.bert_model(**tokens)[0] # assuming a distilbert model here
vecs = self.compressor(vecs)
# if encoding only, zero-out the mask values so we can compress storage
if sequence_type == "doc_encode" or sequence_type == "query_encode":
vecs = vecs * tokens["tokens"]["mask"].unsqueeze(-1)
return vecs
def forward_aggregation(self,query_vecs, document_vecs,query_mask,document_mask):
# create initial term-x-term scores (dot-product)
score = torch.bmm(query_vecs, document_vecs.transpose(2,1))
# mask out padding on the doc dimension (mask by -1000, because max should not select those, setting it to 0 might select them)
exp_mask = document_mask.bool().unsqueeze(1).expand(-1,score.shape[1],-1)
score[~exp_mask] = - 10000
# max pooling over document dimension
score = score.max(-1).values
# mask out paddding query values
score[~(query_mask.bool())] = 0
# sum over query values
score = score.sum(-1)
return score
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased") # honestly not sure if that is the best way to go, but it works :)
model = ColBERT.from_pretrained("sebastian-hofstaetter/colbert-distilbert-margin_mse-T2-msmarco")
````
## Effectiveness on MSMARCO Passage & TREC Deep Learning '19
We trained our model on the MSMARCO standard ("small"-400K query) training triples with knowledge distillation with a batch size of 32 on a single consumer-grade GPU (11GB memory).
For re-ranking we used the top-1000 BM25 results.
### MSMARCO-DEV
Here, we use the larger 49K query DEV set (same range as the smaller 7K DEV set, minimal changes possible)
| | MRR@10 | NDCG@10 |
|----------------------------------|--------|---------|
| BM25 | .194 | .241 |
| **Margin-MSE ColBERT** (Re-ranking) | .375 | .436 |
### TREC-DL'19
For MRR we use the recommended binarization point of the graded relevance of 2. This might skew the results when compared to other binarization point numbers.
| | MRR@10 | NDCG@10 |
|----------------------------------|--------|---------|
| BM25 | .689 | .501 |
| **Margin-MSE ColBERT** (Re-ranking) | .878 | .744 |
For more metrics, baselines, info and analysis, please see the paper: https://arxiv.org/abs/2010.02666
## Limitations & Bias
- The model inherits social biases from both DistilBERT and MSMARCO.
- The model is only trained on relatively short passages of MSMARCO (avg. 60 words length), so it might struggle with longer text.
## Citation
If you use our model checkpoint please cite our work as:
```
@misc{hofstaetter2020_crossarchitecture_kd,
title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation},
author={Sebastian Hofst{\"a}tter and Sophia Althammer and Michael Schr{\"o}der and Mete Sertkan and Allan Hanbury},
year={2020},
eprint={2010.02666},
archivePrefix={arXiv},
primaryClass={cs.IR}
}
``` |
AnonymousSub/rule_based_only_classfn_epochs_1_shard_1 | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 4 | null | ---
language: "en"
tags:
- re-ranking
- passage-ranking
- knowledge-distillation
datasets:
- ms_marco
---
# Margin-MSE Trained DistilBERT-Cat (vanilla/mono/concatenated DistilBERT re-ranker)
We provide a retrieval trained DistilBERT-Cat model. Our model is trained with Margin-MSE using a 3 teacher BERT_Cat (concatenated BERT scoring) ensemble on MSMARCO-Passage.
This instance can be used to **re-rank a candidate set**. The architecure is a 6-layer DistilBERT, with an additional single linear layer at the end.
If you want to know more about our simple, yet effective knowledge distillation method for efficient information retrieval models for a variety of student architectures that is used for this model instance check out our paper: https://arxiv.org/abs/2010.02666 🎉
For more information, training data, source code, and a minimal usage example please visit: https://github.com/sebastian-hofstaetter/neural-ranking-kd
## Configuration
- fp16 trained, so fp16 inference shouldn't be a problem
## Model Code
````python
from transformers import AutoTokenizer,AutoModel, PreTrainedModel,PretrainedConfig
from typing import Dict
import torch
class BERT_Cat_Config(PretrainedConfig):
model_type = "BERT_Cat"
bert_model: str
trainable: bool = True
class BERT_Cat(PreTrainedModel):
"""
The vanilla/mono BERT concatenated (we lovingly refer to as BERT_Cat) architecture
-> requires input concatenation before model, so that batched input is possible
"""
config_class = BERT_Cat_Config
base_model_prefix = "bert_model"
def __init__(self,
cfg) -> None:
super().__init__(cfg)
self.bert_model = AutoModel.from_pretrained(cfg.bert_model)
for p in self.bert_model.parameters():
p.requires_grad = cfg.trainable
self._classification_layer = torch.nn.Linear(self.bert_model.config.hidden_size, 1)
def forward(self,
query_n_doc_sequence):
vecs = self.bert_model(**query_n_doc_sequence)[0][:,0,:] # assuming a distilbert model here
score = self._classification_layer(vecs)
return score
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased") # honestly not sure if that is the best way to go, but it works :)
model = BERT_Cat.from_pretrained("sebastian-hofstaetter/distilbert-cat-margin_mse-T2-msmarco")
````
## Effectiveness on MSMARCO Passage & TREC Deep Learning '19
We trained our model on the MSMARCO standard ("small"-400K query) training triples with knowledge distillation with a batch size of 32 on a single consumer-grade GPU (11GB memory).
For re-ranking we used the top-1000 BM25 results.
### MSMARCO-DEV
Here, we use the larger 49K query DEV set (same range as the smaller 7K DEV set, minimal changes possible)
| | MRR@10 | NDCG@10 |
|----------------------------------|--------|---------|
| BM25 | .194 | .241 |
| **Margin-MSE DistilBERT_Cat** (Re-ranking) | .391 | .451 |
### TREC-DL'19
For MRR we use the recommended binarization point of the graded relevance of 2. This might skew the results when compared to other binarization point numbers.
| | MRR@10 | NDCG@10 |
|----------------------------------|--------|---------|
| BM25 | .689 | .501 |
| **Margin-MSE DistilBERT_Cat** (Re-ranking) | .891 | .747 |
For more metrics, baselines, info and analysis, please see the paper: https://arxiv.org/abs/2010.02666
## Limitations & Bias
- The model inherits social biases from both DistilBERT and MSMARCO.
- The model is only trained on relatively short passages of MSMARCO (avg. 60 words length), so it might struggle with longer text.
## Citation
If you use our model checkpoint please cite our work as:
```
@misc{hofstaetter2020_crossarchitecture_kd,
title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation},
author={Sebastian Hofst{\"a}tter and Sophia Althammer and Michael Schr{\"o}der and Mete Sertkan and Allan Hanbury},
year={2020},
eprint={2010.02666},
archivePrefix={arXiv},
primaryClass={cs.IR}
}
``` |
AnonymousSub/rule_based_only_classfn_epochs_1_shard_1_squad2.0 | [
"pytorch",
"bert",
"question-answering",
"transformers",
"autotrain_compatible"
] | question-answering | {
"architectures": [
"BertForQuestionAnswering"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 2 | null | ---
language: "en"
tags:
- dpr
- dense-passage-retrieval
- knowledge-distillation
datasets:
- ms_marco
---
# DistilBert for Dense Passage Retrieval trained with Balanced Topic Aware Sampling (TAS-B)
We provide a retrieval trained DistilBert-based model (we call the *dual-encoder then dot-product scoring* architecture BERT_Dot) trained with Balanced Topic Aware Sampling on MSMARCO-Passage.
This instance was trained with a batch size of 256 and can be used to **re-rank a candidate set** or **directly for a vector index based dense retrieval**. The architecture is a 6-layer DistilBERT, without architecture additions or modifications (we only change the weights during training) - to receive a query/passage representation we pool the CLS vector. We use the same BERT layers for both query and passage encoding (yields better results, and lowers memory requirements).
If you want to know more about our efficient (can be done on a single consumer GPU in 48 hours) batch composition procedure and dual supervision for dense retrieval training, check out our paper: https://arxiv.org/abs/2104.06967 🎉
For more information and a minimal usage example please visit: https://github.com/sebastian-hofstaetter/tas-balanced-dense-retrieval
## Effectiveness on MSMARCO Passage & TREC-DL'19
We trained our model on the MSMARCO standard ("small"-400K query) training triples re-sampled with our TAS-B method. As teacher models we used the BERT_CAT pairwise scores as well as the ColBERT model for in-batch-negative signals published here: https://github.com/sebastian-hofstaetter/neural-ranking-kd
### MSMARCO-DEV (7K)
| | MRR@10 | NDCG@10 | Recall@1K |
|----------------------------------|--------|---------|-----------------------------|
| BM25 | .194 | .241 | .857 |
| **TAS-B BERT_Dot** (Retrieval) | .347 | .410 | .978 |
### TREC-DL'19
For MRR and Recall we use the recommended binarization point of the graded relevance of 2. This might skew the results when compared to other binarization point numbers.
| | MRR@10 | NDCG@10 | Recall@1K |
|----------------------------------|--------|---------|-----------------------------|
| BM25 | .689 | .501 | .739 |
| **TAS-B BERT_Dot** (Retrieval) | .883 | .717 | .843 |
### TREC-DL'20
For MRR and Recall we use the recommended binarization point of the graded relevance of 2. This might skew the results when compared to other binarization point numbers.
| | MRR@10 | NDCG@10 | Recall@1K |
|----------------------------------|--------|---------|-----------------------------|
| BM25 | .649 | .475 | .806 |
| **TAS-B BERT_Dot** (Retrieval) | .843 | .686 | .875 |
For more baselines, info and analysis, please see the paper: https://arxiv.org/abs/2104.06967
## Limitations & Bias
- The model inherits social biases from both DistilBERT and MSMARCO.
- The model is only trained on relatively short passages of MSMARCO (avg. 60 words length), so it might struggle with longer text.
## Citation
If you use our model checkpoint please cite our work as:
```
@inproceedings{Hofstaetter2021_tasb_dense_retrieval,
author = {Sebastian Hofst{\"a}tter and Sheng-Chieh Lin and Jheng-Hong Yang and Jimmy Lin and Allan Hanbury},
title = {{Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling}},
booktitle = {Proc. of SIGIR},
year = {2021},
}
``` |
AnonymousSub/rule_based_only_classfn_epochs_1_shard_1_wikiqa | [
"pytorch",
"bert",
"text-classification",
"transformers"
] | text-classification | {
"architectures": [
"BertForSequenceClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 32 | null | ---
language: "en"
tags:
- document-retrieval
- knowledge-distillation
datasets:
- ms_marco
---
# Intra-Document Cascading (IDCM)
We provide a retrieval trained IDCM model. Our model is trained on MSMARCO-Document with up to 2000 tokens.
This instance can be used to **re-rank a candidate set** of long documents. The base BERT architecure is a 6-layer DistilBERT.
If you want to know more about our intra document cascading model & training procedure using knowledge distillation check out our paper: https://arxiv.org/abs/2105.09816 🎉
For more information, training data, source code, and a minimal usage example please visit: https://github.com/sebastian-hofstaetter/intra-document-cascade
## Configuration
- Trained with fp16 mixed precision
- We select the top 4 windows of size (50 + 2*7 overlap words) with our fast CK model and score them with BERT
- The published code here is only usable for inference (we removed the training code)
## Model Code
````python
from transformers import AutoTokenizer,AutoModel, PreTrainedModel,PretrainedConfig
from typing import Dict
import torch
from torch import nn as nn
class IDCM_InferenceOnly(PreTrainedModel):
'''
IDCM is a neural re-ranking model for long documents, it creates an intra-document cascade between a fast (CK) and a slow module (BERT_Cat)
This code is only usable for inference (we removed the training mechanism for simplicity)
'''
config_class = IDCM_Config
base_model_prefix = "bert_model"
def __init__(self,
cfg) -> None:
super().__init__(cfg)
#
# bert - scoring
#
if isinstance(cfg.bert_model, str):
self.bert_model = AutoModel.from_pretrained(cfg.bert_model)
else:
self.bert_model = cfg.bert_model
#
# final scoring (combination of bert scores)
#
self._classification_layer = torch.nn.Linear(self.bert_model.config.hidden_size, 1)
self.top_k_chunks = cfg.top_k_chunks
self.top_k_scoring = nn.Parameter(torch.full([1,self.top_k_chunks], 1, dtype=torch.float32, requires_grad=True))
#
# local self attention
#
self.padding_idx= cfg.padding_idx
self.chunk_size = cfg.chunk_size
self.overlap = cfg.overlap
self.extended_chunk_size = self.chunk_size + 2 * self.overlap
#
# sampling stuff
#
self.sample_n = cfg.sample_n
self.sample_context = cfg.sample_context
if self.sample_context == "ck":
i = 3
self.sample_cnn3 = nn.Sequential(
nn.ConstantPad1d((0,i - 1), 0),
nn.Conv1d(kernel_size=i, in_channels=self.bert_model.config.dim, out_channels=self.bert_model.config.dim),
nn.ReLU()
)
elif self.sample_context == "ck-small":
i = 3
self.sample_projector = nn.Linear(self.bert_model.config.dim,384)
self.sample_cnn3 = nn.Sequential(
nn.ConstantPad1d((0,i - 1), 0),
nn.Conv1d(kernel_size=i, in_channels=384, out_channels=128),
nn.ReLU()
)
self.sampling_binweights = nn.Linear(11, 1, bias=True)
torch.nn.init.uniform_(self.sampling_binweights.weight, -0.01, 0.01)
self.kernel_alpha_scaler = nn.Parameter(torch.full([1,1,11], 1, dtype=torch.float32, requires_grad=True))
self.register_buffer("mu",nn.Parameter(torch.tensor([1.0, 0.9, 0.7, 0.5, 0.3, 0.1, -0.1, -0.3, -0.5, -0.7, -0.9]), requires_grad=False).view(1, 1, 1, -1))
self.register_buffer("sigma", nn.Parameter(torch.tensor([0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1]), requires_grad=False).view(1, 1, 1, -1))
def forward(self,
query: Dict[str, torch.LongTensor],
document: Dict[str, torch.LongTensor],
use_fp16:bool = True,
output_secondary_output: bool = False):
#
# patch up documents - local self attention
#
document_ids = document["input_ids"][:,1:]
if document_ids.shape[1] > self.overlap:
needed_padding = self.extended_chunk_size - (((document_ids.shape[1]) % self.chunk_size) - self.overlap)
else:
needed_padding = self.extended_chunk_size - self.overlap - document_ids.shape[1]
orig_doc_len = document_ids.shape[1]
document_ids = nn.functional.pad(document_ids,(self.overlap, needed_padding),value=self.padding_idx)
chunked_ids = document_ids.unfold(1,self.extended_chunk_size,self.chunk_size)
batch_size = chunked_ids.shape[0]
chunk_pieces = chunked_ids.shape[1]
chunked_ids_unrolled=chunked_ids.reshape(-1,self.extended_chunk_size)
packed_indices = (chunked_ids_unrolled[:,self.overlap:-self.overlap] != self.padding_idx).any(-1)
orig_packed_indices = packed_indices.clone()
ids_packed = chunked_ids_unrolled[packed_indices]
mask_packed = (ids_packed != self.padding_idx)
total_chunks=chunked_ids_unrolled.shape[0]
packed_query_ids = query["input_ids"].unsqueeze(1).expand(-1,chunk_pieces,-1).reshape(-1,query["input_ids"].shape[1])[packed_indices]
packed_query_mask = query["attention_mask"].unsqueeze(1).expand(-1,chunk_pieces,-1).reshape(-1,query["attention_mask"].shape[1])[packed_indices]
#
# sampling
#
if self.sample_n > -1:
#
# ck learned matches
#
if self.sample_context == "ck-small":
query_ctx = torch.nn.functional.normalize(self.sample_cnn3(self.sample_projector(self.bert_model.embeddings(packed_query_ids).detach()).transpose(1,2)).transpose(1, 2),p=2,dim=-1)
document_ctx = torch.nn.functional.normalize(self.sample_cnn3(self.sample_projector(self.bert_model.embeddings(ids_packed).detach()).transpose(1,2)).transpose(1, 2),p=2,dim=-1)
elif self.sample_context == "ck":
query_ctx = torch.nn.functional.normalize(self.sample_cnn3((self.bert_model.embeddings(packed_query_ids).detach()).transpose(1,2)).transpose(1, 2),p=2,dim=-1)
document_ctx = torch.nn.functional.normalize(self.sample_cnn3((self.bert_model.embeddings(ids_packed).detach()).transpose(1,2)).transpose(1, 2),p=2,dim=-1)
else:
qe = self.tk_projector(self.bert_model.embeddings(packed_query_ids).detach())
de = self.tk_projector(self.bert_model.embeddings(ids_packed).detach())
query_ctx = self.tk_contextualizer(qe.transpose(1,0),src_key_padding_mask=~packed_query_mask.bool()).transpose(1,0)
document_ctx = self.tk_contextualizer(de.transpose(1,0),src_key_padding_mask=~mask_packed.bool()).transpose(1,0)
query_ctx = torch.nn.functional.normalize(query_ctx,p=2,dim=-1)
document_ctx= torch.nn.functional.normalize(document_ctx,p=2,dim=-1)
cosine_matrix = torch.bmm(query_ctx,document_ctx.transpose(-1, -2)).unsqueeze(-1)
kernel_activations = torch.exp(- torch.pow(cosine_matrix - self.mu, 2) / (2 * torch.pow(self.sigma, 2))) * mask_packed.unsqueeze(-1).unsqueeze(1)
kernel_res = torch.log(torch.clamp(torch.sum(kernel_activations, 2) * self.kernel_alpha_scaler, min=1e-4)) * packed_query_mask.unsqueeze(-1)
packed_patch_scores = self.sampling_binweights(torch.sum(kernel_res, 1))
sampling_scores_per_doc = torch.zeros((total_chunks,1), dtype=packed_patch_scores.dtype, layout=packed_patch_scores.layout, device=packed_patch_scores.device)
sampling_scores_per_doc[packed_indices] = packed_patch_scores
sampling_scores_per_doc = sampling_scores_per_doc.reshape(batch_size,-1,)
sampling_scores_per_doc_orig = sampling_scores_per_doc.clone()
sampling_scores_per_doc[sampling_scores_per_doc == 0] = -9000
sampling_sorted = sampling_scores_per_doc.sort(descending=True)
sampled_indices = sampling_sorted.indices + torch.arange(0,sampling_scores_per_doc.shape[0]*sampling_scores_per_doc.shape[1],sampling_scores_per_doc.shape[1],device=sampling_scores_per_doc.device).unsqueeze(-1)
sampled_indices = sampled_indices[:,:self.sample_n]
sampled_indices_mask = torch.zeros_like(packed_indices).scatter(0, sampled_indices.reshape(-1), 1)
# pack indices
packed_indices = sampled_indices_mask * packed_indices
packed_query_ids = query["input_ids"].unsqueeze(1).expand(-1,chunk_pieces,-1).reshape(-1,query["input_ids"].shape[1])[packed_indices]
packed_query_mask = query["attention_mask"].unsqueeze(1).expand(-1,chunk_pieces,-1).reshape(-1,query["attention_mask"].shape[1])[packed_indices]
ids_packed = chunked_ids_unrolled[packed_indices]
mask_packed = (ids_packed != self.padding_idx)
#
# expensive bert scores
#
bert_vecs = self.forward_representation(torch.cat([packed_query_ids,ids_packed],dim=1),torch.cat([packed_query_mask,mask_packed],dim=1))
packed_patch_scores = self._classification_layer(bert_vecs)
scores_per_doc = torch.zeros((total_chunks,1), dtype=packed_patch_scores.dtype, layout=packed_patch_scores.layout, device=packed_patch_scores.device)
scores_per_doc[packed_indices] = packed_patch_scores
scores_per_doc = scores_per_doc.reshape(batch_size,-1,)
scores_per_doc_orig = scores_per_doc.clone()
scores_per_doc_orig_sorter = scores_per_doc.clone()
if self.sample_n > -1:
scores_per_doc = scores_per_doc * sampled_indices_mask.view(batch_size,-1)
#
# aggregate bert scores
#
if scores_per_doc.shape[1] < self.top_k_chunks:
scores_per_doc = nn.functional.pad(scores_per_doc,(0, self.top_k_chunks - scores_per_doc.shape[1]))
scores_per_doc[scores_per_doc == 0] = -9000
scores_per_doc_orig_sorter[scores_per_doc_orig_sorter == 0] = -9000
score = torch.sort(scores_per_doc,descending=True,dim=-1).values
score[score <= -8900] = 0
score = (score[:,:self.top_k_chunks] * self.top_k_scoring).sum(dim=1)
if self.sample_n == -1:
if output_secondary_output:
return score,{
"packed_indices": orig_packed_indices.view(batch_size,-1),
"bert_scores":scores_per_doc_orig
}
else:
return score,scores_per_doc_orig
else:
if output_secondary_output:
return score,scores_per_doc_orig,{
"score": score,
"packed_indices": orig_packed_indices.view(batch_size,-1),
"sampling_scores":sampling_scores_per_doc_orig,
"bert_scores":scores_per_doc_orig
}
return score
def forward_representation(self, ids,mask,type_ids=None) -> Dict[str, torch.Tensor]:
if self.bert_model.base_model_prefix == 'distilbert': # diff input / output
pooled = self.bert_model(input_ids=ids,
attention_mask=mask)[0][:,0,:]
elif self.bert_model.base_model_prefix == 'longformer':
_, pooled = self.bert_model(input_ids=ids,
attention_mask=mask.long(),
global_attention_mask = ((1-ids)*mask).long())
elif self.bert_model.base_model_prefix == 'roberta': # no token type ids
_, pooled = self.bert_model(input_ids=ids,
attention_mask=mask)
else:
_, pooled = self.bert_model(input_ids=ids,
token_type_ids=type_ids,
attention_mask=mask)
return pooled
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased") # honestly not sure if that is the best way to go, but it works :)
model = IDCM_InferenceOnly.from_pretrained("sebastian-hofstaetter/idcm-distilbert-msmarco_doc")
````
## Effectiveness on MSMARCO Passage & TREC Deep Learning '19
We trained our model on the MSMARCO-Document collection. We trained the selection module CK with knowledge distillation from the stronger BERT model.
For re-ranking we used the top-100 BM25 results. The throughput of IDCM should be ~600 documents with max 2000 tokens per second.
### MSMARCO-Document-DEV
| | MRR@10 | NDCG@10 |
|----------------------------------|--------|---------|
| BM25 | .252 | .311 |
| **IDCM** | .380 | .446 |
### TREC-DL'19 (Document Task)
For MRR we use the recommended binarization point of the graded relevance of 2. This might skew the results when compared to other binarization point numbers.
| | MRR@10 | NDCG@10 |
|----------------------------------|--------|---------|
| BM25 | .661 | .488 |
| **IDCM** | .916 | .688 |
For more metrics, baselines, info and analysis, please see the paper: https://arxiv.org/abs/2105.09816
## Limitations & Bias
- The model inherits social biases from both DistilBERT and MSMARCO.
- The model is only trained on longer documents of MSMARCO, so it might struggle with especially short document text - for short text we recommend one of our MSMARCO-Passage trained models.
## Citation
If you use our model checkpoint please cite our work as:
```
@inproceedings{Hofstaetter2021_idcm,
author = {Sebastian Hofst{\"a}tter and Bhaskar Mitra and Hamed Zamani and Nick Craswell and Allan Hanbury},
title = {{Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking}},
booktitle = {Proc. of SIGIR},
year = {2021},
}
``` |
AnonymousSub/rule_based_only_classfn_twostage_epochs_1_shard_1 | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 10 | null | ---
language: "en"
tags:
- knowledge-distillation
datasets:
- ms_marco
---
# Margin-MSE Trained PreTTR
We provide a retrieval trained DistilBert-based PreTTR model (https://arxiv.org/abs/2004.14255). Our model is trained with Margin-MSE using a 3 teacher BERT_Cat (concatenated BERT scoring) ensemble on MSMARCO-Passage.
This instance can be used to **re-rank a candidate set**. The architecture is a 6-layer DistilBERT, split at layer 3, with an additional single linear layer at the end for scoring the CLS token.
If you want to know more about our simple, yet effective knowledge distillation method for efficient information retrieval models for a variety of student architectures that is used for this model instance check out our paper: https://arxiv.org/abs/2010.02666 🎉
For more information, training data, source code, and a minimal usage example please visit: https://github.com/sebastian-hofstaetter/neural-ranking-kd
## Configuration
- We split the DistilBERT in half at layer 3
## Model Code
````python
from transformers import DistilBertModel,AutoTokenizer
from transformers.models.distilbert.modeling_distilbert import *
import math
import torch
from torch import nn as nn
class PreTTRConfig(DistilBertConfig):
join_layer_idx = 3
class PreTTR(DistilBertModel):
'''
PreTTR changes the distilbert model from huggingface to be able to split query and document until a set layer,
we skipped compression present in the original
from: Efficient Document Re-Ranking for Transformers by Precomputing Term Representations
MacAvaney, et al. https://arxiv.org/abs/2004.14255
'''
config_class = PreTTRConfig
def __init__(self, config):
super().__init__(config)
self.transformer = SplitTransformer(config) # Encoder, we override the classes, but the names stay the same -> so it gets properly initialized
self.embeddings = PosOffsetEmbeddings(config) # Embeddings
self._classification_layer = torch.nn.Linear(self.config.hidden_size, 1, bias=False)
self.join_layer_idx = config.join_layer_idx
def forward(
self,
query,
document,
use_fp16: bool = False) -> torch.Tensor:
with torch.cuda.amp.autocast(enabled=use_fp16):
query_input_ids = query["input_ids"]
query_attention_mask = query["attention_mask"]
document_input_ids = document["input_ids"][:, 1:]
document_attention_mask = document["attention_mask"][:, 1:]
query_embs = self.embeddings(query_input_ids) # (bs, seq_length, dim)
document_embs = self.embeddings(document_input_ids, query_input_ids.shape[-1]) # (bs, seq_length, dim)
tfmr_output = self.transformer(
query_embs=query_embs,
query_mask=query_attention_mask,
doc_embs=document_embs,
doc_mask=document_attention_mask,
join_layer_idx=self.join_layer_idx
)
hidden_state = tfmr_output[0]
score = self._classification_layer(hidden_state[:, 0, :]).squeeze()
return score
class PosOffsetEmbeddings(nn.Module):
def __init__(self, config):
super().__init__()
self.word_embeddings = nn.Embedding(config.vocab_size, config.dim, padding_idx=config.pad_token_id)
self.position_embeddings = nn.Embedding(config.max_position_embeddings, config.dim)
if config.sinusoidal_pos_embds:
create_sinusoidal_embeddings(
n_pos=config.max_position_embeddings, dim=config.dim, out=self.position_embeddings.weight
)
self.LayerNorm = nn.LayerNorm(config.dim, eps=1e-12)
self.dropout = nn.Dropout(config.dropout)
def forward(self, input_ids, pos_offset=0):
"""
Parameters
----------
input_ids: torch.tensor(bs, max_seq_length)
The token ids to embed.
Outputs
-------
embeddings: torch.tensor(bs, max_seq_length, dim)
The embedded tokens (plus position embeddings, no token_type embeddings)
"""
seq_length = input_ids.size(1)
position_ids = torch.arange(seq_length, dtype=torch.long, device=input_ids.device) # (max_seq_length)
position_ids = position_ids.unsqueeze(0).expand_as(input_ids) + pos_offset # (bs, max_seq_length)
word_embeddings = self.word_embeddings(input_ids) # (bs, max_seq_length, dim)
position_embeddings = self.position_embeddings(position_ids) # (bs, max_seq_length, dim)
embeddings = word_embeddings + position_embeddings # (bs, max_seq_length, dim)
embeddings = self.LayerNorm(embeddings) # (bs, max_seq_length, dim)
embeddings = self.dropout(embeddings) # (bs, max_seq_length, dim)
return embeddings
class SplitTransformer(nn.Module):
def __init__(self, config):
super().__init__()
self.n_layers = config.n_layers
layer = TransformerBlock(config)
self.layer = nn.ModuleList([copy.deepcopy(layer) for _ in range(config.n_layers)])
def forward(self, query_embs, query_mask, doc_embs, doc_mask, join_layer_idx, output_attentions=False, output_hidden_states=False):
"""
Parameters
----------
x: torch.tensor(bs, seq_length, dim)
Input sequence embedded.
attn_mask: torch.tensor(bs, seq_length)
Attention mask on the sequence.
Outputs
-------
hidden_state: torch.tensor(bs, seq_length, dim)
Sequence of hiddens states in the last (top) layer
all_hidden_states: Tuple[torch.tensor(bs, seq_length, dim)]
Tuple of length n_layers with the hidden states from each layer.
Optional: only if output_hidden_states=True
all_attentions: Tuple[torch.tensor(bs, n_heads, seq_length, seq_length)]
Tuple of length n_layers with the attention weights from each layer
Optional: only if output_attentions=True
"""
all_hidden_states = ()
all_attentions = ()
#
# query / doc sep.
#
hidden_state_q = query_embs
hidden_state_d = doc_embs
for layer_module in self.layer[:join_layer_idx]:
layer_outputs_q = layer_module(
x=hidden_state_q, attn_mask=query_mask, head_mask=None, output_attentions=output_attentions
)
hidden_state_q = layer_outputs_q[-1]
layer_outputs_d = layer_module(
x=hidden_state_d, attn_mask=doc_mask, head_mask=None, output_attentions=output_attentions
)
hidden_state_d = layer_outputs_d[-1]
#
# combine
#
x = torch.cat([hidden_state_q, hidden_state_d], dim=1)
attn_mask = torch.cat([query_mask, doc_mask], dim=1)
#
# combined
#
hidden_state = x
for layer_module in self.layer[join_layer_idx:]:
layer_outputs = layer_module(
x=hidden_state, attn_mask=attn_mask, head_mask=None, output_attentions=output_attentions
)
hidden_state = layer_outputs[-1]
# Add last layer
if output_hidden_states:
all_hidden_states = all_hidden_states + (hidden_state,)
outputs = (hidden_state,)
if output_hidden_states:
outputs = outputs + (all_hidden_states,)
if output_attentions:
outputs = outputs + (all_attentions,)
return outputs # last-layer hidden state, (all hidden states), (all attentions)
#
# init the model & tokenizer (using the distilbert tokenizer)
#
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased") # honestly not sure if that is the best way to go, but it works :)
model = PreTTR.from_pretrained("sebastian-hofstaetter/prettr-distilbert-split_at_3-margin_mse-T2-msmarco")
````
## Effectiveness on MSMARCO Passage
We trained our model on the MSMARCO standard ("small"-400K query) training triples with knowledge distillation with a batch size of 32 on a single consumer-grade GPU (11GB memory).
For re-ranking we used the top-1000 BM25 results.
### MSMARCO-DEV
Here, we use the larger 49K query DEV set (same range as the smaller 7K DEV set, minimal changes possible)
| | MRR@10 | NDCG@10 |
|----------------------------------|--------|---------|
| BM25 | .194 | .241 |
| **Margin-MSE PreTTR** (Re-ranking) | .386 | .447 |
For more metrics, baselines, info and analysis, please see the paper: https://arxiv.org/abs/2010.02666
## Limitations & Bias
- The model inherits social biases from both DistilBERT and MSMARCO.
- The model is only trained on relatively short passages of MSMARCO (avg. 60 words length), so it might struggle with longer text.
## Citation
If you use our model checkpoint please cite our work as:
```
@misc{hofstaetter2020_crossarchitecture_kd,
title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation},
author={Sebastian Hofst{\"a}tter and Sophia Althammer and Michael Schr{\"o}der and Mete Sertkan and Allan Hanbury},
year={2020},
eprint={2010.02666},
archivePrefix={arXiv},
primaryClass={cs.IR}
}
``` |
AnonymousSub/rule_based_roberta_twostage_quadruplet_epochs_1_shard_10 | [
"pytorch",
"roberta",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"RobertaModel"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 3 | null | ---
language: en
pipeline_tag: zero-shot-classification
tags:
- squeezebert
datasets:
- mulit_nli
metrics:
- accuracy
---
# SqueezeBERT |
AnonymousSub/rule_based_roberta_twostagetriplet_hier_epochs_1_shard_1_wikiqa | [
"pytorch",
"roberta",
"text-classification",
"transformers"
] | text-classification | {
"architectures": [
"RobertaForSequenceClassification"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 23 | null | ---
tags:
- generated_from_trainer
model_index:
- name: koelectra-long-qa
results:
- task:
name: Question Answering
type: question-answering
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# koelectra-long-qa
This model is a fine-tuned version of [monologg/koelectra-base-v3-discriminator](https://huggingface.co/monologg/koelectra-base-v3-discriminator) on an unkown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.8.2
- Pytorch 1.8.1
- Datasets 1.9.0
- Tokenizers 0.10.3
|
AnonymousSub/rule_based_twostage_quadruplet_epochs_1_shard_1 | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 6 | null | ---
tags:
- generated_from_trainer
model_index:
- name: koelectra-qa
results:
- task:
name: Question Answering
type: question-answering
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# koelectra-qa
This model was trained from scratch on an unkown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
### Training results
### Framework versions
- Transformers 4.8.2
- Pytorch 1.8.1
- Datasets 1.9.0
- Tokenizers 0.10.3
|
AnonymousSub/specter-emanuals-model | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 6 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
language: en
license: apache-2.0
---
# all-MiniLM-L12-v1
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/all-MiniLM-L12-v1')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L12-v1')
model = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L12-v1')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/all-MiniLM-L12-v1)
------
## Background
The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised
contrastive learning objective. We used the pretrained [`microsoft/MiniLM-L12-H384-uncased`](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) model and fine-tuned in on a
1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset.
We developped this model during the
[Community week using JAX/Flax for NLP & CV](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104),
organized by Hugging Face. We developped this model as part of the project:
[Train the Best Sentence Embedding Model Ever with 1B Training Pairs](https://discuss.huggingface.co/t/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs/7354). We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks.
## Intended uses
Our model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures
the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks.
By default, input text longer than 128 word pieces is truncated.
## Training procedure
### Pre-training
We use the pretrained [`microsoft/MiniLM-L12-H384-uncased`](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased). Please refer to the model card for more detailed information about the pre-training procedure.
### Fine-tuning
We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch.
We then apply the cross entropy loss by comparing with true pairs.
#### Hyper parameters
We trained ou model on a TPU v3-8. We train the model during 540k steps using a batch size of 1024 (128 per TPU core).
We use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with
a 2e-5 learning rate. The full training script is accessible in this current repository: `train_script.py`.
#### Training data
We use the concatenation from multiple datasets to fine-tune our model. The total number of sentence pairs is above 1 billion sentences.
We sampled each dataset given a weighted probability which configuration is detailed in the `data_config.json` file.
| Dataset | Paper | Number of training tuples |
|--------------------------------------------------------|:----------------------------------------:|:--------------------------:|
| [Reddit comments (2015-2018)](https://github.com/PolyAI-LDN/conversational-datasets/tree/master/reddit) | [paper](https://arxiv.org/abs/1904.06472) | 726,484,430 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Abstracts) | [paper](https://aclanthology.org/2020.acl-main.447/) | 116,288,806 |
| [WikiAnswers](https://github.com/afader/oqa#wikianswers-corpus) Duplicate question pairs | [paper](https://doi.org/10.1145/2623330.2623677) | 77,427,422 |
| [PAQ](https://github.com/facebookresearch/PAQ) (Question, Answer) pairs | [paper](https://arxiv.org/abs/2102.07033) | 64,371,441 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Titles) | [paper](https://aclanthology.org/2020.acl-main.447/) | 52,603,982 |
| [S2ORC](https://github.com/allenai/s2orc) (Title, Abstract) | [paper](https://aclanthology.org/2020.acl-main.447/) | 41,769,185 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Body) pairs | - | 25,316,456 |
| [MS MARCO](https://microsoft.github.io/msmarco/) triplets | [paper](https://doi.org/10.1145/3404835.3462804) | 9,144,553 |
| [GOOAQ: Open Question Answering with Diverse Answer Types](https://github.com/allenai/gooaq) | [paper](https://arxiv.org/pdf/2104.08727.pdf) | 3,012,496 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 1,198,260 |
| [Code Search](https://huggingface.co/datasets/code_search_net) | - | 1,151,414 |
| [COCO](https://cocodataset.org/#home) Image captions | [paper](https://link.springer.com/chapter/10.1007%2F978-3-319-10602-1_48) | 828,395|
| [SPECTER](https://github.com/allenai/specter) citation triplets | [paper](https://doi.org/10.18653/v1/2020.acl-main.207) | 684,100 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Question, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 681,164 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Question) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 659,896 |
| [SearchQA](https://huggingface.co/datasets/search_qa) | [paper](https://arxiv.org/abs/1704.05179) | 582,261 |
| [Eli5](https://huggingface.co/datasets/eli5) | [paper](https://doi.org/10.18653/v1/p19-1346) | 325,475 |
| [Flickr 30k](https://shannon.cs.illinois.edu/DenotationGraph/) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/229/33) | 317,695 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles) | | 304,525 |
| AllNLI ([SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) | [paper SNLI](https://doi.org/10.18653/v1/d15-1075), [paper MultiNLI](https://doi.org/10.18653/v1/n18-1101) | 277,230 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (bodies) | | 250,519 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles+bodies) | | 250,460 |
| [Sentence Compression](https://github.com/google-research-datasets/sentence-compression) | [paper](https://www.aclweb.org/anthology/D13-1155/) | 180,000 |
| [Wikihow](https://github.com/pvl/wikihow_pairs_dataset) | [paper](https://arxiv.org/abs/1810.09305) | 128,542 |
| [Altlex](https://github.com/chridey/altlex/) | [paper](https://aclanthology.org/P16-1135.pdf) | 112,696 |
| [Quora Question Triplets](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) | - | 103,663 |
| [Simple Wikipedia](https://cs.pomona.edu/~dkauchak/simplification/) | [paper](https://www.aclweb.org/anthology/P11-2117/) | 102,225 |
| [Natural Questions (NQ)](https://ai.google.com/research/NaturalQuestions) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/1455) | 100,231 |
| [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/) | [paper](https://aclanthology.org/P18-2124.pdf) | 87,599 |
| [TriviaQA](https://huggingface.co/datasets/trivia_qa) | - | 73,346 |
| **Total** | | **1,124,818,467** | |
AnonymousSub/unsup-consert-base | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 6 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
language: en
license: apache-2.0
datasets:
- s2orc
- flax-sentence-embeddings/stackexchange_xml
- MS Marco
- gooaq
- yahoo_answers_topics
- code_search_net
- search_qa
- eli5
- snli
- multi_nli
- wikihow
- natural_questions
- trivia_qa
- embedding-data/sentence-compression
- embedding-data/flickr30k-captions
- embedding-data/altlex
- embedding-data/simple-wiki
- embedding-data/QQP
- embedding-data/SPECTER
- embedding-data/PAQ_pairs
- embedding-data/WikiAnswers
---
# all-MiniLM-L12-v2
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/all-MiniLM-L12-v2')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L12-v2')
model = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L12-v2')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/all-MiniLM-L12-v2)
------
## Background
The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised
contrastive learning objective. We used the pretrained [`microsoft/MiniLM-L12-H384-uncased`](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) model and fine-tuned in on a
1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset.
We developped this model during the
[Community week using JAX/Flax for NLP & CV](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104),
organized by Hugging Face. We developped this model as part of the project:
[Train the Best Sentence Embedding Model Ever with 1B Training Pairs](https://discuss.huggingface.co/t/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs/7354). We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks.
## Intended uses
Our model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures
the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks.
By default, input text longer than 256 word pieces is truncated.
## Training procedure
### Pre-training
We use the pretrained [`microsoft/MiniLM-L12-H384-uncased`](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) model. Please refer to the model card for more detailed information about the pre-training procedure.
### Fine-tuning
We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch.
We then apply the cross entropy loss by comparing with true pairs.
#### Hyper parameters
We trained ou model on a TPU v3-8. We train the model during 100k steps using a batch size of 1024 (128 per TPU core).
We use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with
a 2e-5 learning rate. The full training script is accessible in this current repository: `train_script.py`.
#### Training data
We use the concatenation from multiple datasets to fine-tune our model. The total number of sentence pairs is above 1 billion sentences.
We sampled each dataset given a weighted probability which configuration is detailed in the `data_config.json` file.
| Dataset | Paper | Number of training tuples |
|--------------------------------------------------------|:----------------------------------------:|:--------------------------:|
| [Reddit comments (2015-2018)](https://github.com/PolyAI-LDN/conversational-datasets/tree/master/reddit) | [paper](https://arxiv.org/abs/1904.06472) | 726,484,430 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Abstracts) | [paper](https://aclanthology.org/2020.acl-main.447/) | 116,288,806 |
| [WikiAnswers](https://github.com/afader/oqa#wikianswers-corpus) Duplicate question pairs | [paper](https://doi.org/10.1145/2623330.2623677) | 77,427,422 |
| [PAQ](https://github.com/facebookresearch/PAQ) (Question, Answer) pairs | [paper](https://arxiv.org/abs/2102.07033) | 64,371,441 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Titles) | [paper](https://aclanthology.org/2020.acl-main.447/) | 52,603,982 |
| [S2ORC](https://github.com/allenai/s2orc) (Title, Abstract) | [paper](https://aclanthology.org/2020.acl-main.447/) | 41,769,185 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Body) pairs | - | 25,316,456 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title+Body, Answer) pairs | - | 21,396,559 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Answer) pairs | - | 21,396,559 |
| [MS MARCO](https://microsoft.github.io/msmarco/) triplets | [paper](https://doi.org/10.1145/3404835.3462804) | 9,144,553 |
| [GOOAQ: Open Question Answering with Diverse Answer Types](https://github.com/allenai/gooaq) | [paper](https://arxiv.org/pdf/2104.08727.pdf) | 3,012,496 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 1,198,260 |
| [Code Search](https://huggingface.co/datasets/code_search_net) | - | 1,151,414 |
| [COCO](https://cocodataset.org/#home) Image captions | [paper](https://link.springer.com/chapter/10.1007%2F978-3-319-10602-1_48) | 828,395|
| [SPECTER](https://github.com/allenai/specter) citation triplets | [paper](https://doi.org/10.18653/v1/2020.acl-main.207) | 684,100 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Question, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 681,164 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Question) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 659,896 |
| [SearchQA](https://huggingface.co/datasets/search_qa) | [paper](https://arxiv.org/abs/1704.05179) | 582,261 |
| [Eli5](https://huggingface.co/datasets/eli5) | [paper](https://doi.org/10.18653/v1/p19-1346) | 325,475 |
| [Flickr 30k](https://shannon.cs.illinois.edu/DenotationGraph/) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/229/33) | 317,695 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles) | | 304,525 |
| AllNLI ([SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) | [paper SNLI](https://doi.org/10.18653/v1/d15-1075), [paper MultiNLI](https://doi.org/10.18653/v1/n18-1101) | 277,230 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (bodies) | | 250,519 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles+bodies) | | 250,460 |
| [Sentence Compression](https://github.com/google-research-datasets/sentence-compression) | [paper](https://www.aclweb.org/anthology/D13-1155/) | 180,000 |
| [Wikihow](https://github.com/pvl/wikihow_pairs_dataset) | [paper](https://arxiv.org/abs/1810.09305) | 128,542 |
| [Altlex](https://github.com/chridey/altlex/) | [paper](https://aclanthology.org/P16-1135.pdf) | 112,696 |
| [Quora Question Triplets](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) | - | 103,663 |
| [Simple Wikipedia](https://cs.pomona.edu/~dkauchak/simplification/) | [paper](https://www.aclweb.org/anthology/P11-2117/) | 102,225 |
| [Natural Questions (NQ)](https://ai.google.com/research/NaturalQuestions) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/1455) | 100,231 |
| [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/) | [paper](https://aclanthology.org/P18-2124.pdf) | 87,599 |
| [TriviaQA](https://huggingface.co/datasets/trivia_qa) | - | 73,346 |
| **Total** | | **1,170,060,424** | |
AnonymousSub/unsup-consert-base_copy | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 6 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
language: en
license: apache-2.0
---
# all-MiniLM-L6-v1
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v1')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v1')
model = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L6-v1')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/all-MiniLM-L6-v1)
------
## Background
The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised
contrastive learning objective. We used the pretrained [`nreimers/MiniLM-L6-H384-uncased`](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) model and fine-tuned in on a
1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset.
We developped this model during the
[Community week using JAX/Flax for NLP & CV](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104),
organized by Hugging Face. We developped this model as part of the project:
[Train the Best Sentence Embedding Model Ever with 1B Training Pairs](https://discuss.huggingface.co/t/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs/7354). We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks.
## Intended uses
Our model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures
the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks.
By default, input text longer than 128 word pieces is truncated.
## Training procedure
### Pre-training
We use the pretrained [`nreimers/MiniLM-L6-H384-uncased`](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) model. Please refer to the model card for more detailed information about the pre-training procedure.
### Fine-tuning
We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch.
We then apply the cross entropy loss by comparing with true pairs.
#### Hyper parameters
We trained ou model on a TPU v3-8. We train the model during 100k steps using a batch size of 1024 (128 per TPU core).
We use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with
a 2e-5 learning rate. The full training script is accessible in this current repository: `train_script.py`.
#### Training data
We use the concatenation from multiple datasets to fine-tune our model. The total number of sentence pairs is above 1 billion sentences.
We sampled each dataset given a weighted probability which configuration is detailed in the `data_config.json` file.
| Dataset | Paper | Number of training tuples |
|--------------------------------------------------------|:----------------------------------------:|:--------------------------:|
| [Reddit comments (2015-2018)](https://github.com/PolyAI-LDN/conversational-datasets/tree/master/reddit) | [paper](https://arxiv.org/abs/1904.06472) | 726,484,430 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Abstracts) | [paper](https://aclanthology.org/2020.acl-main.447/) | 116,288,806 |
| [WikiAnswers](https://github.com/afader/oqa#wikianswers-corpus) Duplicate question pairs | [paper](https://doi.org/10.1145/2623330.2623677) | 77,427,422 |
| [PAQ](https://github.com/facebookresearch/PAQ) (Question, Answer) pairs | [paper](https://arxiv.org/abs/2102.07033) | 64,371,441 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Titles) | [paper](https://aclanthology.org/2020.acl-main.447/) | 52,603,982 |
| [S2ORC](https://github.com/allenai/s2orc) (Title, Abstract) | [paper](https://aclanthology.org/2020.acl-main.447/) | 41,769,185 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Body) pairs | - | 25,316,456 |
| [MS MARCO](https://microsoft.github.io/msmarco/) triplets | [paper](https://doi.org/10.1145/3404835.3462804) | 9,144,553 |
| [GOOAQ: Open Question Answering with Diverse Answer Types](https://github.com/allenai/gooaq) | [paper](https://arxiv.org/pdf/2104.08727.pdf) | 3,012,496 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 1,198,260 |
| [Code Search](https://huggingface.co/datasets/code_search_net) | - | 1,151,414 |
| [COCO](https://cocodataset.org/#home) Image captions | [paper](https://link.springer.com/chapter/10.1007%2F978-3-319-10602-1_48) | 828,395|
| [SPECTER](https://github.com/allenai/specter) citation triplets | [paper](https://doi.org/10.18653/v1/2020.acl-main.207) | 684,100 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Question, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 681,164 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Question) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 659,896 |
| [SearchQA](https://huggingface.co/datasets/search_qa) | [paper](https://arxiv.org/abs/1704.05179) | 582,261 |
| [Eli5](https://huggingface.co/datasets/eli5) | [paper](https://doi.org/10.18653/v1/p19-1346) | 325,475 |
| [Flickr 30k](https://shannon.cs.illinois.edu/DenotationGraph/) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/229/33) | 317,695 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles) | | 304,525 |
| AllNLI ([SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) | [paper SNLI](https://doi.org/10.18653/v1/d15-1075), [paper MultiNLI](https://doi.org/10.18653/v1/n18-1101) | 277,230 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (bodies) | | 250,519 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles+bodies) | | 250,460 |
| [Sentence Compression](https://github.com/google-research-datasets/sentence-compression) | [paper](https://www.aclweb.org/anthology/D13-1155/) | 180,000 |
| [Wikihow](https://github.com/pvl/wikihow_pairs_dataset) | [paper](https://arxiv.org/abs/1810.09305) | 128,542 |
| [Altlex](https://github.com/chridey/altlex/) | [paper](https://aclanthology.org/P16-1135.pdf) | 112,696 |
| [Quora Question Triplets](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) | - | 103,663 |
| [Simple Wikipedia](https://cs.pomona.edu/~dkauchak/simplification/) | [paper](https://www.aclweb.org/anthology/P11-2117/) | 102,225 |
| [Natural Questions (NQ)](https://ai.google.com/research/NaturalQuestions) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/1455) | 100,231 |
| [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/) | [paper](https://aclanthology.org/P18-2124.pdf) | 87,599 |
| [TriviaQA](https://huggingface.co/datasets/trivia_qa) | - | 73,346 |
| **Total** | | **1,124,818,467** | |
AnonymousSub/unsup-consert-base_squad2.0 | [
"pytorch",
"bert",
"question-answering",
"transformers",
"autotrain_compatible"
] | question-answering | {
"architectures": [
"BertForQuestionAnswering"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 2 | 2021-08-18T06:02:11Z | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
language: en
license: apache-2.0
datasets:
- s2orc
- flax-sentence-embeddings/stackexchange_xml
- MS Marco
- gooaq
- yahoo_answers_topics
- code_search_net
- search_qa
- eli5
- snli
- multi_nli
- wikihow
- natural_questions
- trivia_qa
- embedding-data/sentence-compression
- embedding-data/flickr30k-captions
- embedding-data/altlex
- embedding-data/simple-wiki
- embedding-data/QQP
- embedding-data/SPECTER
- embedding-data/PAQ_pairs
- embedding-data/WikiAnswers
---
# all-distilroberta-v1
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/all-distilroberta-v1')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-distilroberta-v1')
model = AutoModel.from_pretrained('sentence-transformers/all-distilroberta-v1')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/all-distilroberta-v1)
------
## Background
The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised
contrastive learning objective. We used the pretrained [`distilroberta-base`](https://huggingface.co/distilroberta-base) model and fine-tuned in on a
1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset.
We developped this model during the
[Community week using JAX/Flax for NLP & CV](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104),
organized by Hugging Face. We developped this model as part of the project:
[Train the Best Sentence Embedding Model Ever with 1B Training Pairs](https://discuss.huggingface.co/t/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs/7354). We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks.
## Intended uses
Our model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures
the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks.
By default, input text longer than 128 word pieces is truncated.
## Training procedure
### Pre-training
We use the pretrained [`distilroberta-base`](https://huggingface.co/distilroberta-base). Please refer to the model card for more detailed information about the pre-training procedure.
### Fine-tuning
We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch.
We then apply the cross entropy loss by comparing with true pairs.
#### Hyper parameters
We trained ou model on a TPU v3-8. We train the model during 920k steps using a batch size of 512 (64 per TPU core).
We use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with
a 2e-5 learning rate. The full training script is accessible in this current repository: `train_script.py`.
#### Training data
We use the concatenation from multiple datasets to fine-tune our model. The total number of sentence pairs is above 1 billion sentences.
We sampled each dataset given a weighted probability which configuration is detailed in the `data_config.json` file.
| Dataset | Paper | Number of training tuples |
|--------------------------------------------------------|:----------------------------------------:|:--------------------------:|
| [Reddit comments (2015-2018)](https://github.com/PolyAI-LDN/conversational-datasets/tree/master/reddit) | [paper](https://arxiv.org/abs/1904.06472) | 726,484,430 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Abstracts) | [paper](https://aclanthology.org/2020.acl-main.447/) | 116,288,806 |
| [WikiAnswers](https://github.com/afader/oqa#wikianswers-corpus) Duplicate question pairs | [paper](https://doi.org/10.1145/2623330.2623677) | 77,427,422 |
| [PAQ](https://github.com/facebookresearch/PAQ) (Question, Answer) pairs | [paper](https://arxiv.org/abs/2102.07033) | 64,371,441 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Titles) | [paper](https://aclanthology.org/2020.acl-main.447/) | 52,603,982 |
| [S2ORC](https://github.com/allenai/s2orc) (Title, Abstract) | [paper](https://aclanthology.org/2020.acl-main.447/) | 41,769,185 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Body) pairs | - | 25,316,456 |
| [MS MARCO](https://microsoft.github.io/msmarco/) triplets | [paper](https://doi.org/10.1145/3404835.3462804) | 9,144,553 |
| [GOOAQ: Open Question Answering with Diverse Answer Types](https://github.com/allenai/gooaq) | [paper](https://arxiv.org/pdf/2104.08727.pdf) | 3,012,496 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 1,198,260 |
| [Code Search](https://huggingface.co/datasets/code_search_net) | - | 1,151,414 |
| [COCO](https://cocodataset.org/#home) Image captions | [paper](https://link.springer.com/chapter/10.1007%2F978-3-319-10602-1_48) | 828,395|
| [SPECTER](https://github.com/allenai/specter) citation triplets | [paper](https://doi.org/10.18653/v1/2020.acl-main.207) | 684,100 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Question, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 681,164 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Question) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 659,896 |
| [SearchQA](https://huggingface.co/datasets/search_qa) | [paper](https://arxiv.org/abs/1704.05179) | 582,261 |
| [Eli5](https://huggingface.co/datasets/eli5) | [paper](https://doi.org/10.18653/v1/p19-1346) | 325,475 |
| [Flickr 30k](https://shannon.cs.illinois.edu/DenotationGraph/) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/229/33) | 317,695 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles) | | 304,525 |
| AllNLI ([SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) | [paper SNLI](https://doi.org/10.18653/v1/d15-1075), [paper MultiNLI](https://doi.org/10.18653/v1/n18-1101) | 277,230 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (bodies) | | 250,519 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles+bodies) | | 250,460 |
| [Sentence Compression](https://github.com/google-research-datasets/sentence-compression) | [paper](https://www.aclweb.org/anthology/D13-1155/) | 180,000 |
| [Wikihow](https://github.com/pvl/wikihow_pairs_dataset) | [paper](https://arxiv.org/abs/1810.09305) | 128,542 |
| [Altlex](https://github.com/chridey/altlex/) | [paper](https://aclanthology.org/P16-1135.pdf) | 112,696 |
| [Quora Question Triplets](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) | - | 103,663 |
| [Simple Wikipedia](https://cs.pomona.edu/~dkauchak/simplification/) | [paper](https://www.aclweb.org/anthology/P11-2117/) | 102,225 |
| [Natural Questions (NQ)](https://ai.google.com/research/NaturalQuestions) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/1455) | 100,231 |
| [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/) | [paper](https://aclanthology.org/P18-2124.pdf) | 87,599 |
| [TriviaQA](https://huggingface.co/datasets/trivia_qa) | - | 73,346 |
| **Total** | | **1,124,818,467** | |
AnonymousSub/unsup-consert-emanuals | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 2 | 2021-08-18T11:16:39Z | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
language: en
license: apache-2.0
---
# all-mpnet-base-v1
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/all-mpnet-base-v1')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-mpnet-base-v1')
model = AutoModel.from_pretrained('sentence-transformers/all-mpnet-base-v1')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/all-mpnet-base-v1)
------
## Background
The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised
contrastive learning objective. We used the pretrained [`microsoft/mpnet-base`](https://huggingface.co/microsoft/mpnet-base) model and fine-tuned in on a
1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset.
We developped this model during the
[Community week using JAX/Flax for NLP & CV](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104),
organized by Hugging Face. We developped this model as part of the project:
[Train the Best Sentence Embedding Model Ever with 1B Training Pairs](https://discuss.huggingface.co/t/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs/7354). We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks.
## Intended uses
Our model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures
the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks.
By default, input text longer than 128 word pieces is truncated.
## Training procedure
### Pre-training
We use the pretrained [`microsoft/mpnet-base`](https://huggingface.co/microsoft/mpnet-base). Please refer to the model card for more detailed information about the pre-training procedure.
### Fine-tuning
We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch.
We then apply the cross entropy loss by comparing with true pairs.
#### Hyper parameters
We trained ou model on a TPU v3-8. We train the model during 920k steps using a batch size of 512 (64 per TPU core).
We use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with
a 2e-5 learning rate. The full training script is accessible in this current repository: `train_script.py`.
#### Training data
We use the concatenation from multiple datasets to fine-tune our model. The total number of sentence pairs is above 1 billion sentences.
We sampled each dataset given a weighted probability which configuration is detailed in the `data_config.json` file.
| Dataset | Paper | Number of training tuples |
|--------------------------------------------------------|:----------------------------------------:|:--------------------------:|
| [Reddit comments (2015-2018)](https://github.com/PolyAI-LDN/conversational-datasets/tree/master/reddit) | [paper](https://arxiv.org/abs/1904.06472) | 726,484,430 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Abstracts) | [paper](https://aclanthology.org/2020.acl-main.447/) | 116,288,806 |
| [WikiAnswers](https://github.com/afader/oqa#wikianswers-corpus) Duplicate question pairs | [paper](https://doi.org/10.1145/2623330.2623677) | 77,427,422 |
| [PAQ](https://github.com/facebookresearch/PAQ) (Question, Answer) pairs | [paper](https://arxiv.org/abs/2102.07033) | 64,371,441 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Titles) | [paper](https://aclanthology.org/2020.acl-main.447/) | 52,603,982 |
| [S2ORC](https://github.com/allenai/s2orc) (Title, Abstract) | [paper](https://aclanthology.org/2020.acl-main.447/) | 41,769,185 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Body) pairs | - | 25,316,456 |
| [MS MARCO](https://microsoft.github.io/msmarco/) triplets | [paper](https://doi.org/10.1145/3404835.3462804) | 9,144,553 |
| [GOOAQ: Open Question Answering with Diverse Answer Types](https://github.com/allenai/gooaq) | [paper](https://arxiv.org/pdf/2104.08727.pdf) | 3,012,496 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 1,198,260 |
| [Code Search](https://huggingface.co/datasets/code_search_net) | - | 1,151,414 |
| [COCO](https://cocodataset.org/#home) Image captions | [paper](https://link.springer.com/chapter/10.1007%2F978-3-319-10602-1_48) | 828,395|
| [SPECTER](https://github.com/allenai/specter) citation triplets | [paper](https://doi.org/10.18653/v1/2020.acl-main.207) | 684,100 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Question, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 681,164 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Question) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 659,896 |
| [SearchQA](https://huggingface.co/datasets/search_qa) | [paper](https://arxiv.org/abs/1704.05179) | 582,261 |
| [Eli5](https://huggingface.co/datasets/eli5) | [paper](https://doi.org/10.18653/v1/p19-1346) | 325,475 |
| [Flickr 30k](https://shannon.cs.illinois.edu/DenotationGraph/) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/229/33) | 317,695 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles) | | 304,525 |
| AllNLI ([SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) | [paper SNLI](https://doi.org/10.18653/v1/d15-1075), [paper MultiNLI](https://doi.org/10.18653/v1/n18-1101) | 277,230 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (bodies) | | 250,519 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles+bodies) | | 250,460 |
| [Sentence Compression](https://github.com/google-research-datasets/sentence-compression) | [paper](https://www.aclweb.org/anthology/D13-1155/) | 180,000 |
| [Wikihow](https://github.com/pvl/wikihow_pairs_dataset) | [paper](https://arxiv.org/abs/1810.09305) | 128,542 |
| [Altlex](https://github.com/chridey/altlex/) | [paper](https://aclanthology.org/P16-1135.pdf) | 112,696 |
| [Quora Question Triplets](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) | - | 103,663 |
| [Simple Wikipedia](https://cs.pomona.edu/~dkauchak/simplification/) | [paper](https://www.aclweb.org/anthology/P11-2117/) | 102,225 |
| [Natural Questions (NQ)](https://ai.google.com/research/NaturalQuestions) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/1455) | 100,231 |
| [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/) | [paper](https://aclanthology.org/P18-2124.pdf) | 87,599 |
| [TriviaQA](https://huggingface.co/datasets/trivia_qa) | - | 73,346 |
| **Total** | | **1,124,818,467** | |
AnonymousSub/unsup-consert-papers-bert | [
"pytorch",
"bert",
"feature-extraction",
"transformers"
] | feature-extraction | {
"architectures": [
"BertModel"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 9 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
language: en
license: apache-2.0
datasets:
- s2orc
- flax-sentence-embeddings/stackexchange_xml
- MS Marco
- gooaq
- yahoo_answers_topics
- code_search_net
- search_qa
- eli5
- snli
- multi_nli
- wikihow
- natural_questions
- trivia_qa
- embedding-data/sentence-compression
- embedding-data/flickr30k-captions
- embedding-data/altlex
- embedding-data/simple-wiki
- embedding-data/QQP
- embedding-data/SPECTER
- embedding-data/PAQ_pairs
- embedding-data/WikiAnswers
---
# all-mpnet-base-v2
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-mpnet-base-v2')
model = AutoModel.from_pretrained('sentence-transformers/all-mpnet-base-v2')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/all-mpnet-base-v2)
------
## Background
The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised
contrastive learning objective. We used the pretrained [`microsoft/mpnet-base`](https://huggingface.co/microsoft/mpnet-base) model and fine-tuned in on a
1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset.
We developped this model during the
[Community week using JAX/Flax for NLP & CV](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104),
organized by Hugging Face. We developped this model as part of the project:
[Train the Best Sentence Embedding Model Ever with 1B Training Pairs](https://discuss.huggingface.co/t/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs/7354). We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks.
## Intended uses
Our model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures
the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks.
By default, input text longer than 384 word pieces is truncated.
## Training procedure
### Pre-training
We use the pretrained [`microsoft/mpnet-base`](https://huggingface.co/microsoft/mpnet-base) model. Please refer to the model card for more detailed information about the pre-training procedure.
### Fine-tuning
We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch.
We then apply the cross entropy loss by comparing with true pairs.
#### Hyper parameters
We trained ou model on a TPU v3-8. We train the model during 100k steps using a batch size of 1024 (128 per TPU core).
We use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with
a 2e-5 learning rate. The full training script is accessible in this current repository: `train_script.py`.
#### Training data
We use the concatenation from multiple datasets to fine-tune our model. The total number of sentence pairs is above 1 billion sentences.
We sampled each dataset given a weighted probability which configuration is detailed in the `data_config.json` file.
| Dataset | Paper | Number of training tuples |
|--------------------------------------------------------|:----------------------------------------:|:--------------------------:|
| [Reddit comments (2015-2018)](https://github.com/PolyAI-LDN/conversational-datasets/tree/master/reddit) | [paper](https://arxiv.org/abs/1904.06472) | 726,484,430 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Abstracts) | [paper](https://aclanthology.org/2020.acl-main.447/) | 116,288,806 |
| [WikiAnswers](https://github.com/afader/oqa#wikianswers-corpus) Duplicate question pairs | [paper](https://doi.org/10.1145/2623330.2623677) | 77,427,422 |
| [PAQ](https://github.com/facebookresearch/PAQ) (Question, Answer) pairs | [paper](https://arxiv.org/abs/2102.07033) | 64,371,441 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Titles) | [paper](https://aclanthology.org/2020.acl-main.447/) | 52,603,982 |
| [S2ORC](https://github.com/allenai/s2orc) (Title, Abstract) | [paper](https://aclanthology.org/2020.acl-main.447/) | 41,769,185 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Body) pairs | - | 25,316,456 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title+Body, Answer) pairs | - | 21,396,559 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Answer) pairs | - | 21,396,559 |
| [MS MARCO](https://microsoft.github.io/msmarco/) triplets | [paper](https://doi.org/10.1145/3404835.3462804) | 9,144,553 |
| [GOOAQ: Open Question Answering with Diverse Answer Types](https://github.com/allenai/gooaq) | [paper](https://arxiv.org/pdf/2104.08727.pdf) | 3,012,496 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 1,198,260 |
| [Code Search](https://huggingface.co/datasets/code_search_net) | - | 1,151,414 |
| [COCO](https://cocodataset.org/#home) Image captions | [paper](https://link.springer.com/chapter/10.1007%2F978-3-319-10602-1_48) | 828,395|
| [SPECTER](https://github.com/allenai/specter) citation triplets | [paper](https://doi.org/10.18653/v1/2020.acl-main.207) | 684,100 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Question, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 681,164 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Question) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 659,896 |
| [SearchQA](https://huggingface.co/datasets/search_qa) | [paper](https://arxiv.org/abs/1704.05179) | 582,261 |
| [Eli5](https://huggingface.co/datasets/eli5) | [paper](https://doi.org/10.18653/v1/p19-1346) | 325,475 |
| [Flickr 30k](https://shannon.cs.illinois.edu/DenotationGraph/) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/229/33) | 317,695 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles) | | 304,525 |
| AllNLI ([SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) | [paper SNLI](https://doi.org/10.18653/v1/d15-1075), [paper MultiNLI](https://doi.org/10.18653/v1/n18-1101) | 277,230 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (bodies) | | 250,519 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles+bodies) | | 250,460 |
| [Sentence Compression](https://github.com/google-research-datasets/sentence-compression) | [paper](https://www.aclweb.org/anthology/D13-1155/) | 180,000 |
| [Wikihow](https://github.com/pvl/wikihow_pairs_dataset) | [paper](https://arxiv.org/abs/1810.09305) | 128,542 |
| [Altlex](https://github.com/chridey/altlex/) | [paper](https://aclanthology.org/P16-1135.pdf) | 112,696 |
| [Quora Question Triplets](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) | - | 103,663 |
| [Simple Wikipedia](https://cs.pomona.edu/~dkauchak/simplification/) | [paper](https://www.aclweb.org/anthology/P11-2117/) | 102,225 |
| [Natural Questions (NQ)](https://ai.google.com/research/NaturalQuestions) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/1455) | 100,231 |
| [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/) | [paper](https://aclanthology.org/P18-2124.pdf) | 87,599 |
| [TriviaQA](https://huggingface.co/datasets/trivia_qa) | - | 73,346 |
| **Total** | | **1,170,060,424** | |
AnonymousSubmission/pretrained-model-1 | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
license: apache-2.0
---
# allenai-specter
This model is a conversion of the [AllenAI SPECTER](https://github.com/allenai/specter) model to [sentence-transformers](https://www.SBERT.net). It can be used to map the titles & abstracts of scientific publications to a vector space such that similar papers are close.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/allenai-specter')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
def cls_pooling(model_output, attention_mask):
return model_output[0][:,0]
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/allenai-specter')
model = AutoModel.from_pretrained('sentence-transformers/allenai-specter')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/allenai-specter)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
See [AllenAI SPECTER](https://github.com/allenai/specter) |
Anonymreign/savagebeta | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# average_word_embeddings_glove.6B.300d
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 300 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/average_word_embeddings_glove.6B.300d')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/average_word_embeddings_glove.6B.300d)
## Full Model Architecture
```
SentenceTransformer(
(0): WordEmbeddings(
(emb_layer): Embedding(400001, 300)
)
(1): Pooling({'word_embedding_dimension': 300, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Anorak/nirvana | [
"pytorch",
"pegasus",
"text2text-generation",
"unk",
"dataset:Anorak/autonlp-data-Niravana-test2",
"transformers",
"autonlp",
"co2_eq_emissions",
"autotrain_compatible"
] | text2text-generation | {
"architectures": [
"PegasusForConditionalGeneration"
],
"model_type": "pegasus",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 7 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# average_word_embeddings_glove.840B.300d
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 300 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/average_word_embeddings_glove.840B.300d')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/average_word_embeddings_glove.840B.300d)
## Full Model Architecture
```
SentenceTransformer(
(0): WordEmbeddings(
(emb_layer): Embedding(2196018, 300)
)
(1): Pooling({'word_embedding_dimension': 300, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Anthos23/FS-distilroberta-fine-tuned | [
"pytorch",
"roberta",
"text-classification",
"transformers",
"has_space"
] | text-classification | {
"architectures": [
"RobertaForSequenceClassification"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 33 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# average_word_embeddings_levy_dependency
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 300 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/average_word_embeddings_levy_dependency')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/average_word_embeddings_levy_dependency)
## Full Model Architecture
```
SentenceTransformer(
(0): WordEmbeddings(
(emb_layer): Embedding(174016, 300)
)
(1): Pooling({'word_embedding_dimension': 300, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Anthos23/distilbert-base-uncased-finetuned-sst2 | [
"tf",
"tensorboard",
"distilbert",
"text-classification",
"transformers",
"generated_from_keras_callback",
"license:apache-2.0"
] | text-classification | {
"architectures": [
"DistilBertForSequenceClassification"
],
"model_type": "distilbert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 21 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
license: apache-2.0
---
# bert-base-nli-cls-token
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/bert-base-nli-cls-token')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
def cls_pooling(model_output, attention_mask):
return model_output[0][:,0]
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/bert-base-nli-cls-token')
model = AutoModel.from_pretrained('sentence-transformers/bert-base-nli-cls-token')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/bert-base-nli-cls-token)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Anthos23/my-awesome-model | [
"pytorch",
"tf",
"roberta",
"text-classification",
"transformers"
] | text-classification | {
"architectures": [
"RobertaForSequenceClassification"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 30 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
license: apache-2.0
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/bert-base-nli-max-tokens
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/bert-base-nli-max-tokens')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
# Max Pooling - Take the max value over time for every dimension.
def max_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
token_embeddings[input_mask_expanded == 0] = -1e9 # Set padding tokens to large negative value
return torch.max(token_embeddings, 1)[0]
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/bert-base-nli-max-tokens')
model = AutoModel.from_pretrained('sentence-transformers/bert-base-nli-max-tokens')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = max_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/bert-base-nli-max-tokens)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': True, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Anthos23/sentiment-roberta-large-english-finetuned-sentiment-analysis | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
license: apache-2.0
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/bert-base-nli-mean-tokens
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/bert-base-nli-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/bert-base-nli-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/bert-base-nli-mean-tokens')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/bert-base-nli-mean-tokens)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Anthos23/test_trainer | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | 2020-07-10T09:27:31Z | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
license: apache-2.0
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/bert-base-nli-stsb-mean-tokens
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/bert-base-nli-stsb-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/bert-base-nli-stsb-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/bert-base-nli-stsb-mean-tokens')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/bert-base-nli-stsb-mean-tokens)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
AntonClaesson/finetuning_test | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | 2021-06-22T19:37:44Z | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
license: apache-2.0
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/bert-base-wikipedia-sections-mean-tokens
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/bert-base-wikipedia-sections-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/bert-base-wikipedia-sections-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/bert-base-wikipedia-sections-mean-tokens')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/bert-base-wikipedia-sections-mean-tokens)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
AntonClaesson/movie-plot-generator | [
"pytorch",
"gpt2",
"text-generation",
"transformers"
] | text-generation | {
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": true,
"max_length": 50
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 9 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
license: apache-2.0
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/bert-large-nli-cls-token
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/bert-large-nli-cls-token')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
def cls_pooling(model_output, attention_mask):
return model_output[0][:,0]
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/bert-large-nli-cls-token')
model = AutoModel.from_pretrained('sentence-transformers/bert-large-nli-cls-token')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/bert-large-nli-cls-token)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Anubhav23/IndianlegalBert | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
license: apache-2.0
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/bert-large-nli-mean-tokens
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/bert-large-nli-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/bert-large-nli-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/bert-large-nli-mean-tokens')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/bert-large-nli-mean-tokens)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Anubhav23/indianlegal | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | 2021-06-22T19:46:04Z | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
license: apache-2.0
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/bert-large-nli-stsb-mean-tokens
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/bert-large-nli-stsb-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/bert-large-nli-stsb-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/bert-large-nli-stsb-mean-tokens')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/bert-large-nli-stsb-mean-tokens)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Anubhav23/model_name | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | 2021-06-22T19:47:48Z | ---
pipeline_tag: sentence-similarity
language: multilingual
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
license: apache-2.0
---
# sentence-transformers/clip-ViT-B-32-multilingual-v1
This is a multi-lingual version of the OpenAI CLIP-ViT-B32 model. You can map text (in 50+ languages) and images to a common dense vector space such that images and the matching texts are close. This model can be used for **image search** (users search through a large collection of images) and for **multi-lingual zero-shot image classification** (image labels are defined as text).
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer, util
from PIL import Image, ImageFile
import requests
import torch
# We use the original clip-ViT-B-32 for encoding images
img_model = SentenceTransformer('clip-ViT-B-32')
# Our text embedding model is aligned to the img_model and maps 50+
# languages to the same vector space
text_model = SentenceTransformer('sentence-transformers/clip-ViT-B-32-multilingual-v1')
# Now we load and encode the images
def load_image(url_or_path):
if url_or_path.startswith("http://") or url_or_path.startswith("https://"):
return Image.open(requests.get(url_or_path, stream=True).raw)
else:
return Image.open(url_or_path)
# We load 3 images. You can either pass URLs or
# a path on your disc
img_paths = [
# Dog image
"https://unsplash.com/photos/QtxgNsmJQSs/download?ixid=MnwxMjA3fDB8MXxhbGx8fHx8fHx8fHwxNjM1ODQ0MjY3&w=640",
# Cat image
"https://unsplash.com/photos/9UUoGaaHtNE/download?ixid=MnwxMjA3fDB8MXxzZWFyY2h8Mnx8Y2F0fHwwfHx8fDE2MzU4NDI1ODQ&w=640",
# Beach image
"https://unsplash.com/photos/Siuwr3uCir0/download?ixid=MnwxMjA3fDB8MXxzZWFyY2h8NHx8YmVhY2h8fDB8fHx8MTYzNTg0MjYzMg&w=640"
]
images = [load_image(img) for img in img_paths]
# Map images to the vector space
img_embeddings = img_model.encode(images)
# Now we encode our text:
texts = [
"A dog in the snow",
"Eine Katze", # German: A cat
"Una playa con palmeras." # Spanish: a beach with palm trees
]
text_embeddings = text_model.encode(texts)
# Compute cosine similarities:
cos_sim = util.cos_sim(text_embeddings, img_embeddings)
for text, scores in zip(texts, cos_sim):
max_img_idx = torch.argmax(scores)
print("Text:", text)
print("Score:", scores[max_img_idx] )
print("Path:", img_paths[max_img_idx], "\n")
```
## Multilingual Image Search - Demo
For a demo of multilingual image search, have a look at: [Image_Search-multilingual.ipynb](https://github.com/UKPLab/sentence-transformers/tree/master/examples/applications/image-search/Image_Search-multilingual.ipynb) ( [Colab version](https://colab.research.google.com/drive/1N6woBKL4dzYsHboDNqtv-8gjZglKOZcn?usp=sharing) )
For more details on image search and zero-shot image classification, have a look at the documentation on [SBERT.net](https://www.sbert.net/examples/applications/image-search/README.html).
## Training
This model has been created using [Multilingual Knowledge Distillation](https://arxiv.org/abs/2004.09813). As teacher model, we used the original `clip-ViT-B-32` and then trained a [multilingual DistilBERT](https://huggingface.co/distilbert-base-multilingual-cased) model as student model. Using parallel data, the multilingual student model learns to align the teachers vector space across many languages. As a result, you get an text embedding model that works for 50+ languages.
The image encoder from CLIP is unchanged, i.e. you can use the original CLIP image encoder to encode images.
Have a look at the [SBERT.net - Multilingual-Models documentation](https://www.sbert.net/examples/training/multilingual/README.html) on more details and for **training code**.
We used the following 50+ languages to align the vector spaces: ar, bg, ca, cs, da, de, el, es, et, fa, fi, fr, fr-ca, gl, gu, he, hi, hr, hu, hy, id, it, ja, ka, ko, ku, lt, lv, mk, mn, mr, ms, my, nb, nl, pl, pt, pt, pt-br, ro, ru, sk, sl, sq, sr, sv, th, tr, uk, ur, vi, zh-cn, zh-tw.
The original multilingual DistilBERT supports 100+ lanugages. The model also work for these languages, but might not yield the best results.
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Dense({'in_features': 768, 'out_features': 512, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
gaurishhs/API | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: feature-extraction
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/distilbert-base-nli-max-tokens
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/distilbert-base-nli-max-tokens')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
# Max Pooling - Take the max value over time for every dimension.
def max_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
token_embeddings[input_mask_expanded == 0] = -1e9 # Set padding tokens to large negative value
return torch.max(token_embeddings, 1)[0]
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/distilbert-base-nli-max-tokens')
model = AutoModel.from_pretrained('sentence-transformers/distilbert-base-nli-max-tokens')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = max_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/distilbert-base-nli-max-tokens)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': True, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Apisate/DialoGPT-small-jordan | [
"pytorch",
"gpt2",
"text-generation",
"transformers",
"conversational"
] | conversational | {
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": 1000
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 12 | null | ---
pipeline_tag: feature-extraction
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/distilbert-base-nli-mean-tokens
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/distilbert-base-nli-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/distilbert-base-nli-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/distilbert-base-nli-mean-tokens')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/distilbert-base-nli-mean-tokens)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Apisate/Discord-Ai-Bot | [
"pytorch",
"gpt2",
"text-generation",
"transformers"
] | text-generation | {
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": 1000
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 11 | 2020-08-06T09:26:38Z | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/distilbert-base-nli-stsb-mean-tokens
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/distilbert-base-nli-stsb-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/distilbert-base-nli-stsb-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/distilbert-base-nli-stsb-mean-tokens')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/distilbert-base-nli-stsb-mean-tokens)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Apoorva/k2t-test | [
"pytorch",
"t5",
"text2text-generation",
"en",
"transformers",
"keytotext",
"k2t",
"Keywords to Sentences",
"autotrain_compatible"
] | text2text-generation | {
"architectures": [
"T5ForConditionalGeneration"
],
"model_type": "t5",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": true,
"length_penalty": 2,
"max_length": 200,
"min_length": 30,
"no_repeat_ngram_size": 3,
"num_beams": 4,
"prefix": "summarize: "
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to German: "
},
"translation_en_to_fr": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to French: "
},
"translation_en_to_ro": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to Romanian: "
}
}
} | 7 | 2020-08-28T17:57:11Z | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/distilbert-multilingual-nli-stsb-quora-ranking
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/distilbert-multilingual-nli-stsb-quora-ranking')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/distilbert-multilingual-nli-stsb-quora-ranking')
model = AutoModel.from_pretrained('sentence-transformers/distilbert-multilingual-nli-stsb-quora-ranking')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/distilbert-multilingual-nli-stsb-quora-ranking)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Appolo/TestModel | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/distilroberta-base-msmarco-v1
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/distilroberta-base-msmarco-v1')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/distilroberta-base-msmarco-v1')
model = AutoModel.from_pretrained('sentence-transformers/distilroberta-base-msmarco-v1')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/distilroberta-base-msmarco-v1)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 350, 'do_lower_case': False}) with Transformer model: RobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
ArBert/albert-base-v2-finetuned-ner-agglo-twitter | [
"pytorch",
"tensorboard",
"albert",
"token-classification",
"transformers",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"AlbertForTokenClassification"
],
"model_type": "albert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 27 | 2021-06-22T19:51:42Z | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/distilroberta-base-msmarco-v2
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/distilroberta-base-msmarco-v2')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/distilroberta-base-msmarco-v2')
model = AutoModel.from_pretrained('sentence-transformers/distilroberta-base-msmarco-v2')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/distilroberta-base-msmarco-v2)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 350, 'do_lower_case': False}) with Transformer model: RobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
ArBert/albert-base-v2-finetuned-ner-gmm-twitter | [
"pytorch",
"tensorboard",
"albert",
"token-classification",
"transformers",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"AlbertForTokenClassification"
],
"model_type": "albert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 8 | null | ---
pipeline_tag: sentence-similarity
language: multilingual
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/distiluse-base-multilingual-cased-v1
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 512 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/distiluse-base-multilingual-cased-v1')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/distiluse-base-multilingual-cased-v1)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
ArBert/albert-base-v2-finetuned-ner-gmm | [
"pytorch",
"tensorboard",
"albert",
"token-classification",
"transformers",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"AlbertForTokenClassification"
],
"model_type": "albert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 8 | null | ---
pipeline_tag: sentence-similarity
language: multilingual
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/distiluse-base-multilingual-cased-v2
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 512 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/distiluse-base-multilingual-cased-v2')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/distiluse-base-multilingual-cased-v2)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
ArBert/albert-base-v2-finetuned-ner-kmeans-twitter | [
"pytorch",
"tensorboard",
"albert",
"token-classification",
"transformers",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"AlbertForTokenClassification"
],
"model_type": "albert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 10 | null | ---
pipeline_tag: sentence-similarity
language: multilingual
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/distiluse-base-multilingual-cased
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 512 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/distiluse-base-multilingual-cased')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/distiluse-base-multilingual-cased)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
ArBert/albert-base-v2-finetuned-ner | [
"pytorch",
"tensorboard",
"albert",
"token-classification",
"dataset:conll2003",
"transformers",
"generated_from_trainer",
"license:apache-2.0",
"model-index",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"AlbertForTokenClassification"
],
"model_type": "albert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 19 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/facebook-dpr-ctx_encoder-single-nq-base
This is a port of the [DPR Model](https://github.com/facebookresearch/DPR) to [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/facebook-dpr-ctx_encoder-single-nq-base')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
def cls_pooling(model_output, attention_mask):
return model_output[0][:,0]
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/facebook-dpr-ctx_encoder-single-nq-base')
model = AutoModel.from_pretrained('sentence-transformers/facebook-dpr-ctx_encoder-single-nq-base')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/facebook-dpr-ctx_encoder-single-nq-base)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 509, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
Have a look at: [DPR Model](https://github.com/facebookresearch/DPR) |
ArBert/bert-base-uncased-finetuned-ner-agglo | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/facebook-dpr-question_encoder-multiset-base
This is a port of the [DPR Model](https://github.com/facebookresearch/DPR) to [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/facebook-dpr-question_encoder-multiset-base')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
def cls_pooling(model_output, attention_mask):
return model_output[0][:,0]
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/facebook-dpr-question_encoder-multiset-base')
model = AutoModel.from_pretrained('sentence-transformers/facebook-dpr-question_encoder-multiset-base')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/facebook-dpr-question_encoder-multiset-base)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 509, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
Have a look at: [DPR Model](https://github.com/facebookresearch/DPR) |
ArBert/bert-base-uncased-finetuned-ner-gmm | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/facebook-dpr-question_encoder-single-nq-base
This is a port of the [DPR Model](https://github.com/facebookresearch/DPR) to [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/facebook-dpr-question_encoder-single-nq-base')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
def cls_pooling(model_output, attention_mask):
return model_output[0][:,0]
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/facebook-dpr-question_encoder-single-nq-base')
model = AutoModel.from_pretrained('sentence-transformers/facebook-dpr-question_encoder-single-nq-base')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/facebook-dpr-question_encoder-single-nq-base)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 509, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
Have a look at: [DPR Model](https://github.com/facebookresearch/DPR) |
ArBert/bert-base-uncased-finetuned-ner-kmeans | [
"pytorch",
"tensorboard",
"bert",
"token-classification",
"transformers",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"BertForTokenClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 6 | null | ---
pipeline_tag: sentence-similarity
language: en
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/gtr-t5-large
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space. The model was specifically trained for the task of sematic search.
This model was converted from the Tensorflow model [gtr-large-1](https://tfhub.dev/google/gtr/gtr-large/1) to PyTorch. When using this model, have a look at the publication: [Large Dual Encoders Are Generalizable Retrievers](https://arxiv.org/abs/2112.07899). The tfhub model and this PyTorch model can produce slightly different embeddings, however, when run on the same benchmarks, they produce identical results.
The model uses only the encoder from a T5-large model. The weights are stored in FP16.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/gtr-t5-large')
embeddings = model.encode(sentences)
print(embeddings)
```
The model requires sentence-transformers version 2.2.0 or newer.
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/gtr-t5-large)
## Citing & Authors
If you find this model helpful, please cite the respective publication:
[Large Dual Encoders Are Generalizable Retrievers](https://arxiv.org/abs/2112.07899)
|
ArBert/bert-base-uncased-finetuned-ner | [
"pytorch",
"tensorboard",
"bert",
"token-classification",
"transformers",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"BertForTokenClassification"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 8 | null | ---
pipeline_tag: sentence-similarity
language: en
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/gtr-t5-xl
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space. The model was specifically trained for the task of sematic search.
This model was converted from the Tensorflow model [gtr-xl-1](https://tfhub.dev/google/gtr/gtr-xl/1) to PyTorch. When using this model, have a look at the publication: [Large Dual Encoders Are Generalizable Retrievers](https://arxiv.org/abs/2112.07899). The tfhub model and this PyTorch model can produce slightly different embeddings, however, when run on the same benchmarks, they produce identical results.
The model uses only the encoder from a T5-3B model. The weights are stored in FP16.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/gtr-t5-xl')
embeddings = model.encode(sentences)
print(embeddings)
```
The model requires sentence-transformers version 2.2.0 or newer.
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/gtr-t5-xl)
## Citing & Authors
If you find this model helpful, please cite the respective publication:
[Large Dual Encoders Are Generalizable Retrievers](https://arxiv.org/abs/2112.07899)
|
ArBert/roberta-base-finetuned-ner-agglo-twitter | [
"pytorch",
"tensorboard",
"roberta",
"token-classification",
"transformers",
"generated_from_trainer",
"license:mit",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"RobertaForTokenClassification"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 12 | 2022-02-09T11:13:46Z | ---
pipeline_tag: sentence-similarity
language: en
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/gtr-t5-xxl
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space. The model was specifically trained for the task of sematic search.
This model was converted from the Tensorflow model [gtr-xxl-1](https://tfhub.dev/google/gtr/gtr-xxl/1) to PyTorch. When using this model, have a look at the publication: [Large Dual Encoders Are Generalizable Retrievers](https://arxiv.org/abs/2112.07899). The tfhub model and this PyTorch model can produce slightly different embeddings, however, when run on the same benchmarks, they produce identical results.
The model uses only the encoder from a T5-11B model. The weights are stored in FP16.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/gtr-t5-xxl')
embeddings = model.encode(sentences)
print(embeddings)
```
The model requires sentence-transformers version 2.2.0 or newer.
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/gtr-t5-xxl)
## Citing & Authors
If you find this model helpful, please cite the respective publication:
[Large Dual Encoders Are Generalizable Retrievers](https://arxiv.org/abs/2112.07899)
|
ArBert/roberta-base-finetuned-ner-gmm-twitter | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/msmarco-MiniLM-L-6-v3
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/msmarco-MiniLM-L-6-v3')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/msmarco-MiniLM-L-6-v3')
model = AutoModel.from_pretrained('sentence-transformers/msmarco-MiniLM-L-6-v3')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/msmarco-MiniLM-L-6-v3)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
ArBert/roberta-base-finetuned-ner-gmm | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# msmarco-MiniLM-L12-cos-v5
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and was designed for **semantic search**. It has been trained on 500k (query, answer) pairs from the [MS MARCO Passages dataset](https://github.com/microsoft/MSMARCO-Passage-Ranking). For an introduction to semantic search, have a look at: [SBERT.net - Semantic Search](https://www.sbert.net/examples/applications/semantic-search/README.html)
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer, util
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
#Load the model
model = SentenceTransformer('sentence-transformers/msmarco-MiniLM-L12-cos-v5')
#Encode query and documents
query_emb = model.encode(query)
doc_emb = model.encode(docs)
#Compute dot score between query and all document embeddings
scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the correct pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
#Mean Pooling - Take average of all tokens
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output.last_hidden_state #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
#Encode text
def encode(texts):
# Tokenize sentences
encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input, return_dict=True)
# Perform pooling
embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
return embeddings
# Sentences we want sentence embeddings for
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/msmarco-MiniLM-L12-cos-v5")
model = AutoModel.from_pretrained("sentence-transformers/msmarco-MiniLM-L12-cos-v5")
#Encode query and docs
query_emb = encode(query)
doc_emb = encode(docs)
#Compute dot score between query and all document embeddings
scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Technical Details
In the following some technical details how this model must be used:
| Setting | Value |
| --- | :---: |
| Dimensions | 768 |
| Produces normalized embeddings | Yes |
| Pooling-Method | Mean pooling |
| Suitable score functions | dot-product (`util.dot_score`), cosine-similarity (`util.cos_sim`), or euclidean distance |
Note: When loaded with `sentence-transformers`, this model produces normalized embeddings with length 1. In that case, dot-product and cosine-similarity are equivalent. dot-product is preferred as it is faster. Euclidean distance is proportional to dot-product and can also be used.
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
ArBert/roberta-base-finetuned-ner-kmeans-twitter | [
"pytorch",
"tensorboard",
"roberta",
"token-classification",
"transformers",
"generated_from_trainer",
"license:mit",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"RobertaForTokenClassification"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 10 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# msmarco-MiniLM-L6-cos-v5
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and was designed for **semantic search**. It has been trained on 500k (query, answer) pairs from the [MS MARCO Passages dataset](https://github.com/microsoft/MSMARCO-Passage-Ranking). For an introduction to semantic search, have a look at: [SBERT.net - Semantic Search](https://www.sbert.net/examples/applications/semantic-search/README.html)
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer, util
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
#Load the model
model = SentenceTransformer('sentence-transformers/msmarco-MiniLM-L6-cos-v5')
#Encode query and documents
query_emb = model.encode(query)
doc_emb = model.encode(docs)
#Compute dot score between query and all document embeddings
scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the correct pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
#Mean Pooling - Take average of all tokens
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output.last_hidden_state #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
#Encode text
def encode(texts):
# Tokenize sentences
encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input, return_dict=True)
# Perform pooling
embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
return embeddings
# Sentences we want sentence embeddings for
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/msmarco-MiniLM-L6-cos-v5")
model = AutoModel.from_pretrained("sentence-transformers/msmarco-MiniLM-L6-cos-v5")
#Encode query and docs
query_emb = encode(query)
doc_emb = encode(docs)
#Compute dot score between query and all document embeddings
scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Technical Details
In the following some technical details how this model must be used:
| Setting | Value |
| --- | :---: |
| Dimensions | 384 |
| Produces normalized embeddings | Yes |
| Pooling-Method | Mean pooling |
| Suitable score functions | dot-product (`util.dot_score`), cosine-similarity (`util.cos_sim`), or euclidean distance |
Note: When loaded with `sentence-transformers`, this model produces normalized embeddings with length 1. In that case, dot-product and cosine-similarity are equivalent. dot-product is preferred as it is faster. Euclidean distance is proportional to dot-product and can also be used.
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
ArBert/roberta-base-finetuned-ner-kmeans | [
"pytorch",
"tensorboard",
"roberta",
"token-classification",
"dataset:conll2003",
"transformers",
"generated_from_trainer",
"license:mit",
"model-index",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"RobertaForTokenClassification"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 8 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# msmarco-bert-base-dot-v5
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and was designed for **semantic search**. It has been trained on 500K (query, answer) pairs from the [MS MARCO dataset](https://github.com/microsoft/MSMARCO-Passage-Ranking/). For an introduction to semantic search, have a look at: [SBERT.net - Semantic Search](https://www.sbert.net/examples/applications/semantic-search/README.html)
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer, util
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
#Load the model
model = SentenceTransformer('sentence-transformers/msmarco-bert-base-dot-v5')
#Encode query and documents
query_emb = model.encode(query)
doc_emb = model.encode(docs)
#Compute dot score between query and all document embeddings
scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
print("Query:", query)
for doc, score in doc_score_pairs:
print(score, doc)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the correct pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output.last_hidden_state
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
#Encode text
def encode(texts):
# Tokenize sentences
encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input, return_dict=True)
# Perform pooling
embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
return embeddings
# Sentences we want sentence embeddings for
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/msmarco-bert-base-dot-v5")
model = AutoModel.from_pretrained("sentence-transformers/msmarco-bert-base-dot-v5")
#Encode query and docs
query_emb = encode(query)
doc_emb = encode(docs)
#Compute dot score between query and all document embeddings
scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
print("Query:", query)
for doc, score in doc_score_pairs:
print(score, doc)
```
## Technical Details
In the following some technical details how this model must be used:
| Setting | Value |
| --- | :---: |
| Dimensions | 768 |
| Max Sequence Length | 512 |
| Produces normalized embeddings | No |
| Pooling-Method | Mean pooling |
| Suitable score functions | dot-product (e.g. `util.dot_score`) |
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=msmarco-bert-base-base-dot-v5)
## Training
See `train_script.py` in this repository for the used training script.
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 7858 with parameters:
```
{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MarginMSELoss.MarginMSELoss`
Parameters of the fit()-Method:
```
{
"callback": null,
"epochs": 30,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'transformers.optimization.AdamW'>",
"optimizer_params": {
"lr": 1e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 10000,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: bert-base-uncased
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
ArBert/roberta-base-finetuned-ner | [
"pytorch",
"tensorboard",
"roberta",
"token-classification",
"transformers",
"generated_from_trainer",
"license:mit",
"autotrain_compatible"
] | token-classification | {
"architectures": [
"RobertaForTokenClassification"
],
"model_type": "roberta",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 3 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/msmarco-bert-co-condensor
This is a port of the [Luyu/co-condenser-marco-retriever](https://huggingface.co/Luyu/co-condenser-marco-retriever) model to [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and is optimized for the task of semantic search.
It is based on the paper: [Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval](https://arxiv.org/abs/2108.05540)
## Evaluation
| Model | MS MARCO Dev (MRR@10) | TREC DL 2019 | TREC DL 2020 | FiQA (NDCG@10) | TREC COVID (NDCG@10) | TREC News (NDCG@10) | TREC Robust04 (NDCG@10) |
| ----- | :-------------------: | :----------: | :----------: | :------------: | :------------------: | :-----------------: | :--------------------: |
| [msmarco-roberta-base-ance-firstp](https://huggingface.co/sentence-transformers/msmarco-roberta-base-ance-firstp) | 33.01 | 67.84 | 66.04 | 29.5 | 67.12 | 38.2 | 39.2 |
| [msmarco-bert-co-condensor](https://huggingface.co/sentence-transformers/sentence-transformers/msmarco-bert-co-condensor) | 35.51 | 68.16 | 69.13 |26.04 | 66.89 | 28.54 | 30.71 |
| [msmarco-distilbert-base-tas-b](https://huggingface.co/sentence-transformers/msmarco-distilbert-base-tas-b) | 34.43 | 71.04 | 69.78 | 30.02 | 65.39 | 37.70 | 42.70 |
| [msmarco-distilbert-dot-v5](https://huggingface.co/sentence-transformers/msmarco-distilbert-dot-v5) | 37.25 | 70.14 | 71.08 | 28.61 | 71.96 | 37.88 | 38.29 |
| [msmarco-bert-base-dot-v5](https://huggingface.co/sentence-transformers/msmarco-bert-base-dot-v5) | 38.08 | 70.51 | 73.45 | 32.29 | 74.81 | 38.81 | 42.67 |
For more details on the comparison, see: [SBERT.net - MSMARCO Models](https://www.sbert.net/docs/pretrained-models/msmarco-v5.html)
In the paper, Gao & Callan claim a MS MARCO-Dev score of 38.2 (MRR@10). This is achieved by changing the benchmark: The orginal MS MARCO dataset just provides queries and text passages, from which you must retrieve the relevant passages for a given query.
In their [code](https://github.com/luyug/Dense/blob/454af38e06fe79aac8243b0fa31387c07ee874ab/examples/msmarco-passage-ranking/get_data.sh#L10), they combine the passages with the document titles from MS MARCO document task, i.e. they train and evaluate their model with additional information from a different benchmark. In the above table, the score of 35.41 (MRR@10) is on the MS MARCO Passages benchmark as it is proposed, without having the document titles.
They further trained their model with the document titles, which creates an information leackage: The document titles were re-constructed by the MS MARCO organizers at a later stage for the MS MARCO document benchmark. It was not possible to reconstruct all document titles for all passages. However, the distribution of having a title is not equal for relevant and non-relevant passages: 71.9% of the relevant passages have a document title, while only 64.4% of the non-relevant passages have a title. Hence, the model can learn that, as soon as there is a document title, the probability is higher that this passage is annotated as relevant. It will not make the decision based on the passage content, but by the artifact if there is a title or not.
The information leackage and the change of the benchmark likely leads to the inflated scores reported in the paper.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer, util
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
#Load the model
model = SentenceTransformer('sentence-transformers/msmarco-bert-co-condensor')
#Encode query and documents
query_emb = model.encode(query)
doc_emb = model.encode(docs)
#Compute dot score between query and all document embeddings
scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#CLS Pooling - Take output from first token
def cls_pooling(model_output):
return model_output.last_hidden_state[:,0]
#Encode text
def encode(texts):
# Tokenize sentences
encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input, return_dict=True)
# Perform pooling
embeddings = cls_pooling(model_output)
return embeddings
# Sentences we want sentence embeddings for
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/msmarco-bert-co-condensor")
model = AutoModel.from_pretrained("sentence-transformers/msmarco-bert-co-condensor")
#Encode query and docs
query_emb = encode(query)
doc_emb = encode(docs)
#Compute dot score between query and all document embeddings
scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/msmarco-bert-co-condensor)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
Have a look at: [Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval](https://arxiv.org/abs/2108.05540) |
ArJakusz/DialoGPT-small-stark | [
"pytorch",
"gpt2",
"text-generation",
"transformers",
"conversational"
] | conversational | {
"architectures": [
"GPT2LMHeadModel"
],
"model_type": "gpt2",
"task_specific_params": {
"conversational": {
"max_length": 1000
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 8 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/msmarco-distilbert-base-dot-prod-v3
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/msmarco-distilbert-base-dot-prod-v3')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/msmarco-distilbert-base-dot-prod-v3)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Dense({'in_features': 768, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
ArJakusz/DialoGPT-small-starky | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
language: "en"
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
datasets:
- ms_marco
---
# sentence-transformers/msmarco-distilbert-base-tas-b
This is a port of the [DistilBert TAS-B Model](https://huggingface.co/sebastian-hofstaetter/distilbert-dot-tas_b-b256-msmarco) to [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and is optimized for the task of semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer, util
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
#Load the model
model = SentenceTransformer('sentence-transformers/msmarco-distilbert-base-tas-b')
#Encode query and documents
query_emb = model.encode(query)
doc_emb = model.encode(docs)
#Compute dot score between query and all document embeddings
scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#CLS Pooling - Take output from first token
def cls_pooling(model_output):
return model_output.last_hidden_state[:,0]
#Encode text
def encode(texts):
# Tokenize sentences
encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input, return_dict=True)
# Perform pooling
embeddings = cls_pooling(model_output)
return embeddings
# Sentences we want sentence embeddings for
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/msmarco-distilbert-base-tas-b")
model = AutoModel.from_pretrained("sentence-transformers/msmarco-distilbert-base-tas-b")
#Encode query and docs
query_emb = encode(query)
doc_emb = encode(docs)
#Compute dot score between query and all document embeddings
scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/msmarco-distilbert-base-tas-b)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
Have a look at: [DistilBert TAS-B Model](https://huggingface.co/sebastian-hofstaetter/distilbert-dot-tas_b-b256-msmarco) |
Aracatto/Catto | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/msmarco-distilbert-base-v3
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/msmarco-distilbert-base-v3')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/msmarco-distilbert-base-v3')
model = AutoModel.from_pretrained('sentence-transformers/msmarco-distilbert-base-v3')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/msmarco-distilbert-base-v3)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 510, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Araf/Ummah | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/msmarco-distilbert-base-v4
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/msmarco-distilbert-base-v4')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/msmarco-distilbert-base-v4')
model = AutoModel.from_pretrained('sentence-transformers/msmarco-distilbert-base-v4')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/msmarco-distilbert-base-v4)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
AragornII/DialoGPT-small-harrypotter | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# msmarco-distilbert-cos-v5
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and was designed for **semantic search**. It has been trained on 500k (query, answer) pairs from the [MS MARCO Passages dataset](https://github.com/microsoft/MSMARCO-Passage-Ranking). For an introduction to semantic search, have a look at: [SBERT.net - Semantic Search](https://www.sbert.net/examples/applications/semantic-search/README.html)
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer, util
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
#Load the model
model = SentenceTransformer('sentence-transformers/msmarco-distilbert-cos-v5')
#Encode query and documents
query_emb = model.encode(query)
doc_emb = model.encode(docs)
#Compute dot score between query and all document embeddings
scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the correct pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
#Mean Pooling - Take average of all tokens
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output.last_hidden_state #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
#Encode text
def encode(texts):
# Tokenize sentences
encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input, return_dict=True)
# Perform pooling
embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
return embeddings
# Sentences we want sentence embeddings for
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/msmarco-distilbert-cos-v5")
model = AutoModel.from_pretrained("sentence-transformers/msmarco-distilbert-cos-v5")
#Encode query and docs
query_emb = encode(query)
doc_emb = encode(docs)
#Compute dot score between query and all document embeddings
scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Technical Details
In the following some technical details how this model must be used:
| Setting | Value |
| --- | :---: |
| Dimensions | 768 |
| Produces normalized embeddings | Yes |
| Pooling-Method | Mean pooling |
| Suitable score functions | dot-product (`util.dot_score`), cosine-similarity (`util.cos_sim`), or euclidean distance |
Note: When loaded with `sentence-transformers`, this model produces normalized embeddings with length 1. In that case, dot-product and cosine-similarity are equivalent. dot-product is preferred as it is faster. Euclidean distance is proportional to dot-product and can also be used.
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
ArashEsk95/bert-base-uncased-finetuned-stsb | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | 2021-06-22T21:12:23Z | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# sentence-transformers/msmarco-roberta-base-ance-firstp
This is a port of the [ANCE FirstP Model](https://github.com/microsoft/ANCE/) to [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/msmarco-roberta-base-ance-firstp')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/msmarco-roberta-base-ance-firstp)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: RobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.linear.Identity'})
(3): LayerNorm(
(norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
)
)
```
## Citing & Authors
Have a look at: [ANCE Model](https://github.com/microsoft/ANCE/) |
Archie/myProject | [] | null | {
"architectures": null,
"model_type": null,
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 0 | null | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# multi-qa-MiniLM-L6-dot-v1
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and was designed for **semantic search**. It has been trained on 215M (question, answer) pairs from diverse sources. For an introduction to semantic search, have a look at: [SBERT.net - Semantic Search](https://www.sbert.net/examples/applications/semantic-search/README.html)
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer, util
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
#Load the model
model = SentenceTransformer('sentence-transformers/multi-qa-MiniLM-L6-dot-v1')
#Encode query and documents
query_emb = model.encode(query)
doc_emb = model.encode(docs)
#Compute dot score between query and all document embeddings
scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the correct pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#CLS Pooling - Take output from first token
def cls_pooling(model_output):
return model_output.last_hidden_state[:,0]
#Encode text
def encode(texts):
# Tokenize sentences
encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input, return_dict=True)
# Perform pooling
embeddings = cls_pooling(model_output)
return embeddings
# Sentences we want sentence embeddings for
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/multi-qa-MiniLM-L6-dot-v1")
model = AutoModel.from_pretrained("sentence-transformers/multi-qa-MiniLM-L6-dot-v1")
#Encode query and docs
query_emb = encode(query)
doc_emb = encode(docs)
#Compute dot score between query and all document embeddings
scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Technical Details
In the following some technical details how this model must be used:
| Setting | Value |
| --- | :---: |
| Dimensions | 384 |
| Produces normalized embeddings | No |
| Pooling-Method | CLS pooling |
| Suitable score functions | dot-product (e.g. `util.dot_score`) |
----
## Background
The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised
contrastive learning objective. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset.
We developped this model during the
[Community week using JAX/Flax for NLP & CV](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104),
organized by Hugging Face. We developped this model as part of the project:
[Train the Best Sentence Embedding Model Ever with 1B Training Pairs](https://discuss.huggingface.co/t/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs/7354). We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks.
## Intended uses
Our model is intented to be used for semantic search: It encodes queries / questions and text paragraphs in a dense vector space. It finds relevant documents for the given passages.
Note that there is a limit of 512 word pieces: Text longer than that will be truncated. Further note that the model was just trained on input text up to 250 word pieces. It might not work well for longer text.
## Training procedure
The full training script is accessible in this current repository: `train_script.py`.
### Pre-training
We use the pretrained [`nreimers/MiniLM-L6-H384-uncased`](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) model. Please refer to the model card for more detailed information about the pre-training procedure.
#### Training
We use the concatenation from multiple datasets to fine-tune our model. In total we have about 215M (question, answer) pairs.
We sampled each dataset given a weighted probability which configuration is detailed in the `data_config.json` file.
The model was trained with [MultipleNegativesRankingLoss](https://www.sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) using CLS-pooling, dot-product as similarity function, and a scale of 1.
| Dataset | Number of training tuples |
|--------------------------------------------------------|:--------------------------:|
| [WikiAnswers](https://github.com/afader/oqa#wikianswers-corpus) Duplicate question pairs from WikiAnswers | 77,427,422 |
| [PAQ](https://github.com/facebookresearch/PAQ) Automatically generated (Question, Paragraph) pairs for each paragraph in Wikipedia | 64,371,441 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Body) pairs from all StackExchanges | 25,316,456 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Answer) pairs from all StackExchanges | 21,396,559 |
| [MS MARCO](https://microsoft.github.io/msmarco/) Triplets (query, answer, hard_negative) for 500k queries from Bing search engine | 17,579,773 |
| [GOOAQ: Open Question Answering with Diverse Answer Types](https://github.com/allenai/gooaq) (query, answer) pairs for 3M Google queries and Google featured snippet | 3,012,496 |
| [Amazon-QA](http://jmcauley.ucsd.edu/data/amazon/qa/) (Question, Answer) pairs from Amazon product pages | 2,448,839
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Answer) pairs from Yahoo Answers | 1,198,260 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Question, Answer) pairs from Yahoo Answers | 681,164 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Question) pairs from Yahoo Answers | 659,896 |
| [SearchQA](https://huggingface.co/datasets/search_qa) (Question, Answer) pairs for 140k questions, each with Top5 Google snippets on that question | 582,261 |
| [ELI5](https://huggingface.co/datasets/eli5) (Question, Answer) pairs from Reddit ELI5 (explainlikeimfive) | 325,475 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions pairs (titles) | 304,525 |
| [Quora Question Triplets](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) (Question, Duplicate_Question, Hard_Negative) triplets for Quora Questions Pairs dataset | 103,663 |
| [Natural Questions (NQ)](https://ai.google.com/research/NaturalQuestions) (Question, Paragraph) pairs for 100k real Google queries with relevant Wikipedia paragraph | 100,231 |
| [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/) (Question, Paragraph) pairs from SQuAD2.0 dataset | 87,599 |
| [TriviaQA](https://huggingface.co/datasets/trivia_qa) (Question, Evidence) pairs | 73,346 |
| **Total** | **214,988,242** | |
AryanLala/autonlp-Scientific_Title_Generator-34558227 | [
"pytorch",
"pegasus",
"text2text-generation",
"en",
"dataset:AryanLala/autonlp-data-Scientific_Title_Generator",
"transformers",
"autonlp",
"co2_eq_emissions",
"autotrain_compatible",
"has_space"
] | text2text-generation | {
"architectures": [
"PegasusForConditionalGeneration"
],
"model_type": "pegasus",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 103 | null | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/roberta-base-nli-stsb-mean-tokens
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/roberta-base-nli-stsb-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/roberta-base-nli-stsb-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/roberta-base-nli-stsb-mean-tokens')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/roberta-base-nli-stsb-mean-tokens)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': True}) with Transformer model: RobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Ashkanmh/bert-base-parsbert-uncased-finetuned | [
"pytorch",
"tensorboard",
"bert",
"fill-mask",
"transformers",
"generated_from_trainer",
"autotrain_compatible"
] | fill-mask | {
"architectures": [
"BertForMaskedLM"
],
"model_type": "bert",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 3 | null | ---
pipeline_tag: sentence-similarity
language: en
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# sentence-transformers/sentence-t5-xl
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space. The model works well for sentence similarity tasks, but doesn't perform that well for semantic search tasks.
This model was converted from the Tensorflow model [st5-3b-1](https://tfhub.dev/google/sentence-t5/st5-3b/1) to PyTorch. When using this model, have a look at the publication: [Sentence-T5: Scalable sentence encoders from pre-trained text-to-text models](https://arxiv.org/abs/2108.08877). The tfhub model and this PyTorch model can produce slightly different embeddings, however, when run on the same benchmarks, they produce identical results.
The model uses only the encoder from a T5-3B model. The weights are stored in FP16.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/sentence-t5-xl')
embeddings = model.encode(sentences)
print(embeddings)
```
The model requires sentence-transformers version 2.2.0 or newer.
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/sentence-t5-xl)
## Citing & Authors
If you find this model helpful, please cite the respective publication:
[Sentence-T5: Scalable sentence encoders from pre-trained text-to-text models](https://arxiv.org/abs/2108.08877)
|
Atampy26/GPT-Glacier | [
"pytorch",
"gpt_neo",
"text-generation",
"transformers"
] | text-generation | {
"architectures": [
"GPTNeoForCausalLM"
],
"model_type": "gpt_neo",
"task_specific_params": {
"conversational": {
"max_length": null
},
"summarization": {
"early_stopping": null,
"length_penalty": null,
"max_length": null,
"min_length": null,
"no_repeat_ngram_size": null,
"num_beams": null,
"prefix": null
},
"text-generation": {
"do_sample": null,
"max_length": null
},
"translation_en_to_de": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_fr": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
},
"translation_en_to_ro": {
"early_stopping": null,
"max_length": null,
"num_beams": null,
"prefix": null
}
}
} | 5 | 2021-06-23T06:32:45Z | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/stsb-roberta-base
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/stsb-roberta-base')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/stsb-roberta-base')
model = AutoModel.from_pretrained('sentence-transformers/stsb-roberta-base')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/stsb-roberta-base)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': True}) with Transformer model: RobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.