modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-13 00:37:47
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 555
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-13 00:35:18
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
SaulLu/recreate-history
|
SaulLu
| 2021-05-28T16:37:37Z | 4 | 1 |
transformers
|
[
"transformers",
"pytorch",
"albert",
"token-classification",
"collaborative",
"bengali",
"NER",
"bn",
"dataset:xtreme",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2022-03-02T23:29:04Z |
---
language: bn
tags:
- collaborative
- bengali
- NER
license: apache-2.0
datasets: xtreme
metrics:
- Loss
- Accuracy
- Precision
- Recall
---
# sahajBERT Named Entity Recognition
## Model description
[sahajBERT](https://huggingface.co/neuropark/sahajBERT-NER) fine-tuned for NER using the bengali split of [WikiANN ](https://huggingface.co/datasets/wikiann).
Named Entities predicted by the model:
| Label id | Label |
|:--------:|:----:|
|0 |O|
|1 |B-PER|
|2 |I-PER|
|3 |B-ORG|
|4 |I-ORG|
|5 |B-LOC|
|6 |I-LOC|
## Intended uses & limitations
#### How to use
You can use this model directly with a pipeline for masked language modeling:
```python
from transformers import AlbertForTokenClassification, TokenClassificationPipeline, PreTrainedTokenizerFast
# Initialize tokenizer
tokenizer = PreTrainedTokenizerFast.from_pretrained("neuropark/sahajBERT-NER")
# Initialize model
model = AlbertForTokenClassification.from_pretrained("neuropark/sahajBERT-NER")
# Initialize pipeline
pipeline = TokenClassificationPipeline(tokenizer=tokenizer, model=model)
raw_text = "এই ইউনিয়নে ৩ টি মৌজা ও ১০ টি গ্রাম আছে ।" # Change me
output = pipeline(raw_text)
```
#### Limitations and bias
<!-- Provide examples of latent issues and potential remediations. -->
WIP
## Training data
The model was initialized it with pre-trained weights of [sahajBERT](https://huggingface.co/neuropark/sahajBERT-NER) at step 19519 and trained on the bengali of [WikiANN ](https://huggingface.co/datasets/wikiann)
## Training procedure
Coming soon!
<!-- ```bibtex
@inproceedings{...,
year={2020}
}
``` -->
## Eval results
loss: 0.11714419722557068
accuracy: 0.9772286821705426
precision: 0.9585365853658536
recall: 0.9651277013752456
f1 : 0.9618208516886931
### BibTeX entry and citation info
Coming soon!
<!-- ```bibtex
@inproceedings{...,
year={2020}
}
``` -->
|
allegro/herbert-klej-cased-tokenizer-v1
|
allegro
| 2021-05-28T16:19:05Z | 131 | 1 |
transformers
|
[
"transformers",
"xlm",
"pl",
"endpoints_compatible",
"region:us"
] | null | 2022-03-02T23:29:05Z |
---
language: pl
---
# HerBERT tokenizer
**[HerBERT](https://en.wikipedia.org/wiki/Zbigniew_Herbert)** tokenizer is a character level byte-pair encoding with
vocabulary size of 50k tokens. The tokenizer was trained on [Wolne Lektury](https://wolnelektury.pl/) and a publicly available subset of
[National Corpus of Polish](http://nkjp.pl/index.php?page=14&lang=0) with [fastBPE](https://github.com/glample/fastBPE) library.
Tokenizer utilize `XLMTokenizer` implementation from [transformers](https://github.com/huggingface/transformers).
## Tokenizer usage
Herbert tokenizer should be used together with [HerBERT model](https://huggingface.co/allegro/herbert-klej-cased-v1):
```python
from transformers import XLMTokenizer, RobertaModel
tokenizer = XLMTokenizer.from_pretrained("allegro/herbert-klej-cased-tokenizer-v1")
model = RobertaModel.from_pretrained("allegro/herbert-klej-cased-v1")
encoded_input = tokenizer.encode("Kto ma lepszą sztukę, ma lepszy rząd – to jasne.", return_tensors='pt')
outputs = model(encoded_input)
```
## License
CC BY-SA 4.0
## Citation
If you use this tokenizer, please cite the following paper:
```
@inproceedings{rybak-etal-2020-klej,
title = "{KLEJ}: Comprehensive Benchmark for {P}olish Language Understanding",
author = "Rybak, Piotr and
Mroczkowski, Robert and
Tracz, Janusz and
Gawlik, Ireneusz",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.acl-main.111",
doi = "10.18653/v1/2020.acl-main.111",
pages = "1191--1201",
}
```
## Authors
Tokenizer was created by **Allegro Machine Learning Research** team.
You can contact us at: <a href="mailto:klejbenchmark@allegro.pl">klejbenchmark@allegro.pl</a>
|
allegro/herbert-klej-cased-v1
|
allegro
| 2021-05-28T16:18:22Z | 329 | 6 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"roberta",
"pl",
"arxiv:2005.00630",
"endpoints_compatible",
"region:us"
] | null | 2022-03-02T23:29:05Z |
---
language: pl
---
# HerBERT
**[HerBERT](https://en.wikipedia.org/wiki/Zbigniew_Herbert)** is a BERT-based Language Model trained on Polish Corpora
using only MLM objective with dynamic masking of whole words. For more details, please refer to:
[KLEJ: Comprehensive Benchmark for Polish Language Understanding](https://arxiv.org/abs/2005.00630).
## Dataset
**HerBERT** training dataset is a combination of several publicly available corpora for Polish language:
| Corpus | Tokens | Texts |
| :------ | ------: | ------: |
| [OSCAR](https://traces1.inria.fr/oscar/)| 6710M | 145M |
| [Open Subtitles](http://opus.nlpl.eu/OpenSubtitles-v2018.php) | 1084M | 1.1M |
| [Wikipedia](https://dumps.wikimedia.org/) | 260M | 1.5M |
| [Wolne Lektury](https://wolnelektury.pl/) | 41M | 5.5k |
| [Allegro Articles](https://allegro.pl/artykuly) | 18M | 33k |
## Tokenizer
The training dataset was tokenized into subwords using [HerBERT Tokenizer](https://huggingface.co/allegro/herbert-klej-cased-tokenizer-v1); a character level byte-pair encoding with
a vocabulary size of 50k tokens. The tokenizer itself was trained on [Wolne Lektury](https://wolnelektury.pl/) and a publicly available subset of
[National Corpus of Polish](http://nkjp.pl/index.php?page=14&lang=0) with a [fastBPE](https://github.com/glample/fastBPE) library.
Tokenizer utilizes `XLMTokenizer` implementation for that reason, one should load it as `allegro/herbert-klej-cased-tokenizer-v1`.
## HerBERT models summary
| Model | WWM | Cased | Tokenizer | Vocab Size | Batch Size | Train Steps |
| :------ | ------: | ------: | ------: | ------: | ------: | ------: |
| herbert-klej-cased-v1 | YES | YES | BPE | 50K | 570 | 180k |
## Model evaluation
HerBERT was evaluated on the [KLEJ](https://klejbenchmark.com/) benchmark, publicly available set of nine evaluation tasks for the Polish language understanding.
It had the best average performance and obtained the best results for three of them.
| Model | Average | NKJP-NER | CDSC-E | CDSC-R | CBD | PolEmo2.0-IN\t|PolEmo2.0-OUT | DYK | PSC | AR\t|
| :------ | ------: | ------: | ------: | ------: | ------: | ------: | ------: | ------: | ------: | ------: |
| herbert-klej-cased-v1 | **80.5** | 92.7 | 92.5 | 91.9 | **50.3** | **89.2** |**76.3** |52.1 |95.3 | 84.5 |
Full leaderboard is available [online](https://klejbenchmark.com/leaderboard).
## HerBERT usage
Model training and experiments were conducted with [transformers](https://github.com/huggingface/transformers) in version 2.0.
Example code:
```python
from transformers import XLMTokenizer, RobertaModel
tokenizer = XLMTokenizer.from_pretrained("allegro/herbert-klej-cased-tokenizer-v1")
model = RobertaModel.from_pretrained("allegro/herbert-klej-cased-v1")
encoded_input = tokenizer.encode("Kto ma lepszą sztukę, ma lepszy rząd – to jasne.", return_tensors='pt')
outputs = model(encoded_input)
```
HerBERT can also be loaded using `AutoTokenizer` and `AutoModel`:
```python
tokenizer = AutoTokenizer.from_pretrained("allegro/herbert-klej-cased-tokenizer-v1")
model = AutoModel.from_pretrained("allegro/herbert-klej-cased-v1")
```
## License
CC BY-SA 4.0
## Citation
If you use this model, please cite the following paper:
```
@inproceedings{rybak-etal-2020-klej,
title = "{KLEJ}: Comprehensive Benchmark for {P}olish Language Understanding",
author = "Rybak, Piotr and
Mroczkowski, Robert and
Tracz, Janusz and
Gawlik, Ireneusz",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.acl-main.111",
doi = "10.18653/v1/2020.acl-main.111",
pages = "1191--1201",
}
```
## Authors
The model was trained by **Allegro Machine Learning Research** team.
You can contact us at: <a href="mailto:klejbenchmark@allegro.pl">klejbenchmark@allegro.pl</a>
|
Davlan/xlm-roberta-base-finetuned-yoruba
|
Davlan
| 2021-05-28T13:53:56Z | 11 | 1 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"fill-mask",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2022-03-02T23:29:04Z |
Hugging Face's logo
---
language: yo
datasets:
---
# xlm-roberta-base-finetuned-yoruba
## Model description
**xlm-roberta-base-finetuned-yoruba** is a **Yoruba RoBERTa** model obtained by fine-tuning **xlm-roberta-base** model on Yorùbá language texts. It provides **better performance** than the XLM-RoBERTa on text classification and named entity recognition datasets.
Specifically, this model is a *xlm-roberta-base* model that was fine-tuned on Yorùbá corpus.
## Intended uses & limitations
#### How to use
You can use this model with Transformers *pipeline* for masked token prediction.
```python
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='Davlan/xlm-roberta-base-finetuned-yoruba')
>>> unmasker("Arẹmọ Phillip to jẹ ọkọ <mask> Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun")
[{'sequence': '<s> Arẹmọ Phillip to jẹ ọkọ Queen Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun</s>', 'score': 0.24844281375408173,
'token': 44109,
'token_str': '▁Queen'},
{'sequence': '<s> Arẹmọ Phillip to jẹ ọkọ ile Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun</s>', 'score': 0.1665010154247284,
'token': 1350,
'token_str': '▁ile'},
{'sequence': '<s> Arẹmọ Phillip to jẹ ọkọ ti Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun</s>', 'score': 0.07604238390922546,
'token': 1053,
'token_str': '▁ti'},
{'sequence': '<s> Arẹmọ Phillip to jẹ ọkọ baba Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun</s>', 'score': 0.06353845447301865,
'token': 12878,
'token_str': '▁baba'},
{'sequence': '<s> Arẹmọ Phillip to jẹ ọkọ Oba Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun</s>', 'score': 0.03836742788553238,
'token': 82879,
'token_str': '▁Oba'}]
```
#### Limitations and bias
This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.
## Training data
This model was fine-tuned on Bible, JW300, [Menyo-20k](https://huggingface.co/datasets/menyo20k_mt), [Yoruba Embedding corpus](https://huggingface.co/datasets/yoruba_text_c3) and [CC-Aligned](https://opus.nlpl.eu/), Wikipedia, news corpora (BBC Yoruba, VON Yoruba, Asejere, Alaroye), and other small datasets curated from friends.
## Training procedure
This model was trained on a single NVIDIA V100 GPU
## Eval results on Test set (F-score, average over 5 runs)
Dataset| XLM-R F1 | yo_roberta F1
-|-|-
[MasakhaNER](https://github.com/masakhane-io/masakhane-ner) | 77.58 | 83.66
[BBC Yorùbá Textclass](https://huggingface.co/datasets/yoruba_bbc_topics) | |
### BibTeX entry and citation info
By David Adelani
```
```
|
julien-c/tensorboard-traces
|
julien-c
| 2021-05-28T13:07:49Z | 0 | 2 | null |
[
"tensorboard",
"region:us"
] | null | 2022-03-02T23:29:05Z |
## Dummy model containing only Tensorboard traces
from multiple different experiments
|
castorini/monot5-3b-med-msmarco
|
castorini
| 2021-05-28T11:54:47Z | 5 | 2 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"feature-extraction",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2022-03-02T23:29:05Z |
This model is a T5-3B reranker fine-tuned on the MS MARCO passage dataset for 10K steps (or 1 epoch) and then fine-tuned again on MedMARCO (from [Sledge-Z paper](https://www.aclweb.org/anthology/2020.emnlp-main.341.pdf)) for 1K steps.
For more details on how to use it, check [pygaggle.ai](pygaggle.ai)!
Paper describing the model: [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://www.aclweb.org/anthology/2020.findings-emnlp.63/)
|
m3hrdadfi/bert-fa-base-uncased-farstail-mean-tokens
|
m3hrdadfi
| 2021-05-28T06:03:42Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"bert",
"feature-extraction",
"fa",
"arxiv:2009.08820",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2022-03-02T23:29:05Z |
---
language: fa
license: apache-2.0
---
# FarsTail + ParsBERT
Please follow the [FarsTail](https://github.com/dml-qom/FarsTail) repo for the latest information about the dataset. For accessing the beneficiary models from this dataset, check out the [Sentence-Transformer](https://github.com/m3hrdadfi/sentence-transformers) repo.
```bibtex
@article{amirkhani2020farstail,
title={FarsTail: A Persian Natural Language Inference Dataset},
author={Hossein Amirkhani, Mohammad Azari Jafari, Azadeh Amirak, Zohreh Pourjafari, Soroush Faridan Jahromi, and Zeinab Kouhkan},
journal={arXiv preprint arXiv:2009.08820},
year={2020}
}
```
|
m3hrdadfi/bert-fa-base-uncased-wikitriplet-mean-tokens
|
m3hrdadfi
| 2021-05-28T06:02:17Z | 304 | 1 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"bert",
"feature-extraction",
"fa",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2022-03-02T23:29:05Z |
---
language: fa
license: apache-2.0
---
# ParsBERT + Sentence Transformers
Please follow the [Sentence-Transformer](https://github.com/m3hrdadfi/sentence-transformers) repo for the latest information about previous and current models.
```bibtex
@misc{SentenceTransformerWiki,
author = {Mehrdad Farahani},
title = {Sentence Embeddings with ParsBERT},
year = {2020},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {https://github.com/m3hrdadfi/sentence-transformers},
}
```
|
m3hrdadfi/bert-fa-base-uncased-wikinli
|
m3hrdadfi
| 2021-05-28T06:01:35Z | 20 | 2 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"bert",
"text-classification",
"fa",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2022-03-02T23:29:05Z |
---
language: fa
license: apache-2.0
---
# ParsBERT + Sentence Transformers
Please follow the [Sentence-Transformer](https://github.com/m3hrdadfi/sentence-transformers) repo for the latest information about previous and current models.
```bibtex
@misc{SentenceTransformerWiki,
author = {Mehrdad Farahani},
title = {Sentence Embeddings with ParsBERT},
year = {2020},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {https://github.com/m3hrdadfi/sentence-transformers},
}
```
|
huggingtweets/officialmcafee
|
huggingtweets
| 2021-05-28T04:01:04Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/officialmcafee/1622174431277/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1068211396712763392/7FxhjlR3_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">John McAfee</div>
<div style="text-align: center; font-size: 14px;">@officialmcafee</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from John McAfee.
| Data | John McAfee |
| --- | --- |
| Tweets downloaded | 3226 |
| Retweets | 44 |
| Short tweets | 1884 |
| Tweets kept | 1298 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1wje8sy2/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @officialmcafee's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/n8r5a5dd) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/n8r5a5dd/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/officialmcafee')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/matei_zaharia
|
huggingtweets
| 2021-05-28T01:40:13Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/787317891867693061/isUFxFC1_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">Matei Zaharia</div>
<div style="text-align: center; font-size: 14px;">@matei_zaharia</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from Matei Zaharia.
| Data | Matei Zaharia |
| --- | --- |
| Tweets downloaded | 1497 |
| Retweets | 713 |
| Short tweets | 17 |
| Tweets kept | 767 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3mod3uxt/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @matei_zaharia's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2squr71y) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2squr71y/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/matei_zaharia')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/tatsu_moved
|
huggingtweets
| 2021-05-28T01:37:11Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1394041828245229569/GqycTopw_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">Tatsu Mori / MOVED TO NEW ACCOUNT</div>
<div style="text-align: center; font-size: 14px;">@tatsu_moved</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from Tatsu Mori / MOVED TO NEW ACCOUNT.
| Data | Tatsu Mori / MOVED TO NEW ACCOUNT |
| --- | --- |
| Tweets downloaded | 3247 |
| Retweets | 131 |
| Short tweets | 729 |
| Tweets kept | 2387 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1yst62rv/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @tatsu_moved's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/hn213w51) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/hn213w51/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/tatsu_moved')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/krislikesbooks
|
huggingtweets
| 2021-05-28T00:18:42Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/krislikesbooks/1622161041088/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1393350979114790914/-iM9DS3X_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">kl conrad kilgallen, ma</div>
<div style="text-align: center; font-size: 14px;">@krislikesbooks</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from kl conrad kilgallen, ma.
| Data | kl conrad kilgallen, ma |
| --- | --- |
| Tweets downloaded | 623 |
| Retweets | 132 |
| Short tweets | 26 |
| Tweets kept | 465 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/rgomxad6/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @krislikesbooks's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/i60lm5kw) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/i60lm5kw/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/krislikesbooks')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
m3hrdadfi/icelandic-ner-roberta
|
m3hrdadfi
| 2021-05-27T17:13:07Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"roberta",
"token-classification",
"is",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2022-03-02T23:29:05Z |
---
language: is
license: apache-2.0
widget:
- text: "Kristin manneskja getur ekki lagt frásagnir af Jesú Kristi á hilluna vegna þess að hún sé búin að lesa þær ."
- text: "Til hvers að kjósa flokk , sem þykist vera Jafnaðarmannaflokkur rétt fyrir kosningar , þegar að það er hægt að kjósa sannnan jafnaðarmannaflokk , sjálfan Jafnaðarmannaflokk Íslands - Samfylkinguna ."
- text: "Það sannaðist svo eftirminnilega á plötunni Það þarf fólk eins og þig sem kom út fyrir þremur árum , en á henni hann Fálka úr Keflavík og Gáluna , son sinn , til að útsetja lög hans og spila inn ."
- text: "Lögin hafa áður komið út sem aukalög á smáskífum af Hail to the Thief , en á disknum er líka myndband og fleira efni fyrir tölvur ."
- text: "Britney gerði honum viðvart og hann ók henni á UCLA-sjúkrahúsið í Santa Monica en það er í nágrenni hljóðversins ."
---
# IcelandicNER RoBERTa
This model was fine-tuned on the MIM-GOLD-NER dataset for the Icelandic language.
The [MIM-GOLD-NER](http://hdl.handle.net/20.500.12537/42) corpus was developed at [Reykjavik University](https://en.ru.is/) in 2018–2020 that covered eight types of entities:
- Date
- Location
- Miscellaneous
- Money
- Organization
- Percent
- Person
- Time
## Dataset Information
| | Records | B-Date | B-Location | B-Miscellaneous | B-Money | B-Organization | B-Percent | B-Person | B-Time | I-Date | I-Location | I-Miscellaneous | I-Money | I-Organization | I-Percent | I-Person | I-Time |
|:------|----------:|---------:|-------------:|------------------:|----------:|-----------------:|------------:|-----------:|---------:|---------:|-------------:|------------------:|----------:|-----------------:|------------:|-----------:|---------:|
| Train | 39988 | 3409 | 5980 | 4351 | 729 | 5754 | 502 | 11719 | 868 | 2112 | 516 | 3036 | 770 | 2382 | 50 | 5478 | 790 |
| Valid | 7063 | 570 | 1034 | 787 | 100 | 1078 | 103 | 2106 | 147 | 409 | 76 | 560 | 104 | 458 | 7 | 998 | 136 |
| Test | 8299 | 779 | 1319 | 935 | 153 | 1315 | 108 | 2247 | 172 | 483 | 104 | 660 | 167 | 617 | 10 | 1089 | 158 |
## Evaluation
The following tables summarize the scores obtained by model overall and per each class.
| entity | precision | recall | f1-score | support |
|:-------------:|:---------:|:--------:|:--------:|:-------:|
| Date | 0.961881 | 0.971759 | 0.966794 | 779.0 |
| Location | 0.963047 | 0.968158 | 0.965595 | 1319.0 |
| Miscellaneous | 0.884946 | 0.880214 | 0.882574 | 935.0 |
| Money | 0.980132 | 0.967320 | 0.973684 | 153.0 |
| Organization | 0.924300 | 0.928517 | 0.926404 | 1315.0 |
| Percent | 1.000000 | 1.000000 | 1.000000 | 108.0 |
| Person | 0.978591 | 0.976413 | 0.977501 | 2247.0 |
| Time | 0.965116 | 0.965116 | 0.965116 | 172.0 |
| micro avg | 0.951258 | 0.952476 | 0.951866 | 7028.0 |
| macro avg | 0.957252 | 0.957187 | 0.957209 | 7028.0 |
| weighted avg | 0.951237 | 0.952476 | 0.951849 | 7028.0 |
## How To Use
You use this model with Transformers pipeline for NER.
### Installing requirements
```bash
pip install transformers
```
### How to predict using pipeline
```python
from transformers import AutoTokenizer
from transformers import AutoModelForTokenClassification # for pytorch
from transformers import TFAutoModelForTokenClassification # for tensorflow
from transformers import pipeline
model_name_or_path = "m3hrdadfi/icelandic-ner-roberta"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForTokenClassification.from_pretrained(model_name_or_path) # Pytorch
# model = TFAutoModelForTokenClassification.from_pretrained(model_name_or_path) # Tensorflow
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
example = "Kristin manneskja getur ekki lagt frásagnir af Jesú Kristi á hilluna vegna þess að hún sé búin að lesa þær ."
ner_results = nlp(example)
print(ner_results)
```
## Questions?
Post a Github issue on the [IcelandicNER Issues](https://github.com/m3hrdadfi/icelandic-ner/issues) repo.
|
RaphBL/great-model
|
RaphBL
| 2021-05-27T16:34:11Z | 9 | 0 |
transformers
|
[
"transformers",
"pytorch",
"camembert",
"question-answering",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2022-03-02T23:29:04Z |
GreatModel does not solve any NLP problem ... for exercise purpose only.
|
huggingtweets/gavibegtrup
|
huggingtweets
| 2021-05-27T14:55:49Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/gavibegtrup/1622127344791/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1362440200304041986/nLi9iMVI_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">Gavi Begtrup</div>
<div style="text-align: center; font-size: 14px;">@gavibegtrup</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from Gavi Begtrup.
| Data | Gavi Begtrup |
| --- | --- |
| Tweets downloaded | 990 |
| Retweets | 67 |
| Short tweets | 49 |
| Tweets kept | 874 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1kx48u2r/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @gavibegtrup's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1n9nuiku) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1n9nuiku/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/gavibegtrup')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/puppsicle
|
huggingtweets
| 2021-05-26T19:27:21Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/puppsicle/1622057237543/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1377443014348443657/xkQW2dKC_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">★ pupp</div>
<div style="text-align: center; font-size: 14px;">@puppsicle</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from ★ pupp.
| Data | ★ pupp |
| --- | --- |
| Tweets downloaded | 3181 |
| Retweets | 1945 |
| Short tweets | 95 |
| Tweets kept | 1141 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/38y6m8ix/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @puppsicle's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/yqwoj783) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/yqwoj783/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/puppsicle')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
philschmid/distilroberta-base-ner-wikiann-conll2003-3-class
|
philschmid
| 2021-05-26T14:13:00Z | 23 | 2 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"token-classification",
"dataset:wikiann-conll2003",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2022-03-02T23:29:05Z |
---
license: apache-2.0
tags:
- token-classification
datasets:
- wikiann-conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilroberta-base-ner-wikiann-conll2003-3-class
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wikiann-conll2003
type: wikiann-conll2003
metrics:
- name: Precision
type: precision
value: 0.9624757386241104
- name: Recall
type: recall
value: 0.9667497021553124
- name: F1
type: f1
value: 0.964607986167396
- name: Accuracy
type: accuracy
value: 0.9913626461292995
---
<!-- 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. -->
# distilroberta-base-ner-wikiann-conll2003-3-class
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the wikiann and conll2003 dataset. It consists out of the classes of wikiann.
O (0), B-PER (1), I-PER (2), B-ORG (3), I-ORG (4) B-LOC (5), I-LOC (6).
eval F1-Score: **96,25** (merged dataset)
test F1-Score: **92,41** (merged dataset)
## Model Usage
```python
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained("philschmid/distilroberta-base-ner-wikiann-conll2003-3-class")
model = AutoModelForTokenClassification.from_pretrained("philschmid/distilroberta-base-ner-wikiann-conll2003-3-class")
nlp = pipeline("ner", model=model, tokenizer=tokenizer, grouped_entities=True)
example = "My name is Philipp and live in Germany"
nlp(example)
```
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4.9086903597787154e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
- mixed_precision_training: Native AMP
### Training results
It achieves the following results on the evaluation set:
- Loss: 0.0520
- Precision: 0.9625
- Recall: 0.9667
- F1: 0.9646
- Accuracy: 0.9914
It achieves the following results on the test set:
- Loss: 0.141
- Precision: 0.917
- Recall: 0.9313
- F1: 0.9241
- Accuracy: 0.9807
### Framework versions
- Transformers 4.6.1
- Pytorch 1.8.1+cu101
- Datasets 1.6.2
- Tokenizers 0.10.3
|
huggingtweets/georgenotfound
|
huggingtweets
| 2021-05-26T07:42:03Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/georgenotfound/1622013920235/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1173474608856608768/vEBnPUdm_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">George</div>
<div style="text-align: center; font-size: 14px;">@georgenotfound</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from George.
| Data | George |
| --- | --- |
| Tweets downloaded | 848 |
| Retweets | 6 |
| Short tweets | 310 |
| Tweets kept | 532 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2doc1coj/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @georgenotfound's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/155sbgzb) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/155sbgzb/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/georgenotfound')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
michalwilk123/distilbert-imdb-positive
|
michalwilk123
| 2021-05-25T19:59:11Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"fill-mask",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2022-03-02T23:29:05Z |
distilbert model trained on positive imdb reviews
|
michalwilk123/distilbert-imdb-negative
|
michalwilk123
| 2021-05-25T12:53:19Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"fill-mask",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2022-03-02T23:29:05Z |
distilbert trained on negative imdb reviews
|
kangnichaluo/mnli-4
|
kangnichaluo
| 2021-05-25T12:36:39Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2022-03-02T23:29:05Z |
learning rate: 2e-5
training epochs: 3
batch size: 64
seed: 87
model: bert-base-uncased
trained on MNLI which is converted into two-way nli classification (predict entailment or not-entailment class)
|
kangnichaluo/mnli-1
|
kangnichaluo
| 2021-05-25T11:36:25Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2022-03-02T23:29:05Z |
learning rate: 2e-5
training epochs: 3
batch size: 64
seed: 42
model: bert-base-uncased
trained on MNLI which is converted into two-way nli classification (predict entailment or not-entailment class)
|
sultan/BioM-ELECTRA-Large-Generator
|
sultan
| 2021-05-24T21:07:58Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"electra",
"fill-mask",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2022-03-02T23:29:05Z |
# BioM-Transformers: Building Large Biomedical Language Models with BERT, ALBERT and ELECTRA
# Abstract
The impact of design choices on the performance
of biomedical language models recently
has been a subject for investigation. In
this paper, we empirically study biomedical
domain adaptation with large transformer models
using different design choices. We evaluate
the performance of our pretrained models
against other existing biomedical language
models in the literature. Our results show that
we achieve state-of-the-art results on several
biomedical domain tasks despite using similar
or less computational cost compared to other
models in the literature. Our findings highlight
the significant effect of design choices on
improving the performance of biomedical language
models.
# Model Description
This model was pre-trained on PubMed Abstracts only with biomedical domain vocabulary for 434K steps with a batch size of 4096 on TPUv3-512 unit.
Check our GitHub repo at https://github.com/salrowili/BioM-Transformers for TensorFlow and GluonNLP checkpoints.
# Acknowledgment
We would like to acknowledge the support we have from Tensorflow Research Cloud (TFRC) team to grant us access to TPUv3 units.
# Citation
```bibtex
@inproceedings{alrowili-shanker-2021-biom,
title = "{B}io{M}-Transformers: Building Large Biomedical Language Models with {BERT}, {ALBERT} and {ELECTRA}",
author = "Alrowili, Sultan and
Shanker, Vijay",
booktitle = "Proceedings of the 20th Workshop on Biomedical Language Processing",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2021.bionlp-1.24",
pages = "221--227",
abstract = "The impact of design choices on the performance of biomedical language models recently has been a subject for investigation. In this paper, we empirically study biomedical domain adaptation with large transformer models using different design choices. We evaluate the performance of our pretrained models against other existing biomedical language models in the literature. Our results show that we achieve state-of-the-art results on several biomedical domain tasks despite using similar or less computational cost compared to other models in the literature. Our findings highlight the significant effect of design choices on improving the performance of biomedical language models.",
}
```
|
huggingtweets/orogdk
|
huggingtweets
| 2021-05-24T19:51:55Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/orogdk/1621885910948/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1391236434736992256/n33h-uPP_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">Loggged ̘͇̣̲̃̍̅ ̺ͫͥͣ͋̇̍ ̷̥̉̏Out ̴̵̨̛͢ ̸̶̢̛͘ ͘͏ ̢̡͞</div>
<div style="text-align: center; font-size: 14px;">@orogdk</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from Loggged ̘͇̣̲̃̍̅ ̺ͫͥͣ͋̇̍ ̷̥̉̏Out ̴̵̨̛͢ ̸̶̢̛͘ ͘͏ ̢̡͞.
| Data | Loggged ̘͇̣̲̃̍̅ ̺ͫͥͣ͋̇̍ ̷̥̉̏Out ̴̵̨̛͢ ̸̶̢̛͘ ͘͏ ̢̡͞ |
| --- | --- |
| Tweets downloaded | 173 |
| Retweets | 11 |
| Short tweets | 35 |
| Tweets kept | 127 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3vq1365m/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @orogdk's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2lep1qnl) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2lep1qnl/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/orogdk')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
RecordedFuture/Swedish-Sentiment-Violence-Targets
|
RecordedFuture
| 2021-05-24T13:02:37Z | 31 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"bert",
"token-classification",
"sv",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2022-03-02T23:29:04Z |
---
language: sv
license: mit
---
## Swedish BERT models for sentiment analysis, Sentiment targets.
[Recorded Future](https://www.recordedfuture.com/) together with [AI Sweden](https://www.ai.se/en) releases two language models for target/role assignment in Swedish. The two models are based on the [KB/bert-base-swedish-cased](https://huggingface.co/KB/bert-base-swedish-cased), the models as has been fine tuned to solve a Named Entety Recognition(NER) token classification task.
This is a downstream model to be used in conjunction with the [Swedish violence sentiment classifier](https://huggingface.co/RecordedFuture/Swedish-Sentiment-Violence) or [Swedish violence sentiment classifier](https://huggingface.co/RecordedFuture/Swedish-Sentiment-Fear). The models are trained to tag parts of sentences that has recieved a positive classification from the upstream sentiment classifier. The model will tag parts of sentences that contains the targets that the upstream model has activated on.
The NER sentiment target models do work as standalone models but their recommended application is downstreamfrom a sentence classification model.
The models are only trained on Swedish data and only supports inference of Swedish input texts. The models inference metrics for all non-Swedish inputs are not defined, these inputs are considered as out of domain data.
The current models are supported at Transformers version >= 4.3.3 and Torch version 1.8.0, compatibility with older versions are not verified.
### Fear targets
The model can be imported from the transformers library by running
from transformers import BertForSequenceClassification, BertTokenizerFast
tokenizer = BertTokenizerFast.from_pretrained("RecordedFuture/Swedish-Sentiment-Fear-Targets")
classifier_fear_targets= BertForTokenClassification.from_pretrained("RecordedFuture/Swedish-Sentiment-Fear-Targets")
When the model and tokenizer are initialized the model can be used for inference.
#### Verification metrics
During training the Fear target model had the following verification metrics when using "any overlap" as the evaluation metric.
| F-score | Precision | Recall |
|:-------------------------:|:-------:|:---------:|:------:|
| 0.8361 | 0.7903 | 0.8876 |
#### Swedish-Sentiment-Violence
The model be can imported from the transformers library by running
from transformers import BertForSequenceClassification, BertTokenizerFast
tokenizer = BertTokenizerFast.from_pretrained("RecordedFuture/Swedish-Sentiment-Violence-Targets")
classifier_violence_targets = BertForTokenClassification.from_pretrained("RecordedFuture/Swedish-Sentiment-Violence-Targets")
When the model and tokenizer are initialized the model can be used for inference.
#### Verification metrics
During training the Violence target model had the following verification metrics when using "any overlap" as the evaluation metric.
| F-score | Precision | Recall |
|:-------------------------:|:-------:|:---------:|:------:|
| 0.7831| 0.9155| 0.8442 |
|
huggingtweets/eromaximus
|
huggingtweets
| 2021-05-23T18:12:56Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/eromaximus/1621793572911/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1391474227602153474/wSbqLqAl_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">☆ᗪoubleᗰarshmallow☆</div>
<div style="text-align: center; font-size: 14px;">@eromaximus</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from ☆ᗪoubleᗰarshmallow☆.
| Data | ☆ᗪoubleᗰarshmallow☆ |
| --- | --- |
| Tweets downloaded | 674 |
| Retweets | 388 |
| Short tweets | 46 |
| Tweets kept | 240 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/25ro381p/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @eromaximus's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/c712ca0z) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/c712ca0z/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/eromaximus')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/heaven_ley
|
huggingtweets
| 2021-05-23T14:18:42Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/heaven_ley/1621532679555/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1391998269430116355/O5NJQwYC_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">Ashley 🌻</div>
<div style="text-align: center; font-size: 14px;">@heaven_ley</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from Ashley 🌻.
| Data | Ashley 🌻 |
| --- | --- |
| Tweets downloaded | 3084 |
| Retweets | 563 |
| Short tweets | 101 |
| Tweets kept | 2420 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/h9ex5ztp/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @heaven_ley's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2rr1mtsr) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2rr1mtsr/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/heaven_ley')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/azulcrescent
|
huggingtweets
| 2021-05-23T14:17:13Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/azulcrescent/1621537893204/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1385798100430868486/QusggrjY_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">Azul Crescent</div>
<div style="text-align: center; font-size: 14px;">@azulcrescent</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from Azul Crescent.
| Data | Azul Crescent |
| --- | --- |
| Tweets downloaded | 1039 |
| Retweets | 9 |
| Short tweets | 92 |
| Tweets kept | 938 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3hna2b57/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @azulcrescent's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/23ccs0az) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/23ccs0az/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/azulcrescent')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/pearltrans
|
huggingtweets
| 2021-05-23T14:14:51Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/pearltrans/1621529245791/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1389950688331960324/7bkgN6h8_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">PearlTheComicsGirl</div>
<div style="text-align: center; font-size: 14px;">@pearltrans</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from PearlTheComicsGirl.
| Data | PearlTheComicsGirl |
| --- | --- |
| Tweets downloaded | 837 |
| Retweets | 100 |
| Short tweets | 166 |
| Tweets kept | 571 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/szcek6ld/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @pearltrans's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3t5jniyr) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3t5jniyr/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/pearltrans')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/mitll
|
huggingtweets
| 2021-05-23T14:13:26Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/mitll/1621527157401/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1380233126354558979/ltnN7Gl4_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">Lincoln Laboratory</div>
<div style="text-align: center; font-size: 14px;">@mitll</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from Lincoln Laboratory.
| Data | Lincoln Laboratory |
| --- | --- |
| Tweets downloaded | 2054 |
| Retweets | 569 |
| Short tweets | 14 |
| Tweets kept | 1471 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2k9mrbjd/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @mitll's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/b55wa3e8) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/b55wa3e8/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/mitll')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
vmicheli/lm-butlers-gpt
|
vmicheli
| 2021-05-23T13:37:59Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"arxiv:2104.07972",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
GPT model developed in [Language Models are Few-Shot Butlers](https://arxiv.org/abs/2104.07972).
|
vasudevgupta/dl-hack-gpt2-large
|
vasudevgupta
| 2021-05-23T13:34:31Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
DL research papers **Title -> abstract**
**Using this model**
```python
from transformers import pipeline, GPT2LMHeadModel, GPT2Tokenizer
tokenizer = GPT2Tokenizer.from_pretrained("vasudevgupta/dl-hack-gpt2-large")
model = GPT2LMHeadModel.from_pretrained("vasudevgupta/dl-hack-gpt2-large")
agent = pipeline("text-generation", model=model, tokenizer=tokenizer)
print(agent("An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale", max_length=200))
```
|
stevhliu/astroGPT
|
stevhliu
| 2021-05-23T12:59:14Z | 139 | 5 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"gpt2",
"text-generation",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: "en"
thumbnail: "https://raw.githubusercontent.com/stevhliu/satsuma/master/images/astroGPT-thumbnail.png"
widget:
- text: "Jan 18, 2020"
- text: "Feb 14, 2020"
- text: "Jul 04, 2020"
---
# astroGPT 🪐
## Model description
This is a GPT-2 model fine-tuned on Western zodiac signs. For more information about GPT-2, take a look at 🤗 Hugging Face's GPT-2 [model card](https://huggingface.co/gpt2). You can use astroGPT to generate a daily horoscope by entering the current date.
## How to use
To use this model, simply enter the current date like so `Mon DD, YEAR`:
```python
from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained("stevhliu/astroGPT")
model = AutoModelWithLMHead.from_pretrained("stevhliu/astroGPT")
input_ids = tokenizer.encode('Sep 03, 2020', return_tensors='pt').to('cuda')
sample_output = model.generate(input_ids,
do_sample=True,
max_length=75,
top_k=20,
top_p=0.97)
print(sample_output)
```
## Limitations and bias
astroGPT inherits the same biases that affect GPT-2 as a result of training on a lot of non-neutral content on the internet. The model does not currently support zodiac sign-specific generation and only returns a general horoscope. While the generated text may occasionally mention a specific zodiac sign, this is due to how the horoscopes were originally written by it's human authors.
## Data
The data was scraped from [Horoscope.com](https://www.horoscope.com/us/index.aspx) and trained on 4.7MB of text. The text was collected from four categories (daily, love, wellness, career) and span from 09/01/19 to 08/01/2020. The archives only store horoscopes dating a year back from the current date.
## Training and results
The text was tokenized using the fast GPT-2 BPE [tokenizer](https://huggingface.co/transformers/model_doc/gpt2.html#gpt2tokenizerfast). It has a vocabulary size of 50,257 and sequence length of 1024 tokens. The model was trained with on one of Google Colaboratory's GPU's for approximately 2.5 hrs with [fastai's](https://docs.fast.ai/) learning rate finder, discriminative learning rates and 1cycle policy. See table below for a quick summary of the training procedure and results.
| dataset size | epochs | lr | training time | train_loss | valid_loss | perplexity |
|:-------------:|:------:|:-----------------:|:-------------:|:----------:|:----------:|:----------:|
| 5.9MB |32 | slice(1e-7,1e-5) | 2.5 hrs | 2.657170 | 2.642387 | 14.046692 |
|
rjbownes/Magic-The-Generating
|
rjbownes
| 2021-05-23T12:17:20Z | 5 | 1 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
widget:
- text: "Even the Dwarves"
- text: "The secrets of"
---
# Model name
Magic The Generating
## Model description
This is a fine tuned GPT-2 model trained on a corpus of all available English language Magic the Gathering card flavour texts.
## Intended uses & limitations
This is intended only for use in generating new, novel, and sometimes surprising, MtG like flavour texts.
#### How to use
```python
from transformers import GPT2Tokenizer, GPT2LMHeadModel
tokenizer = GPT2Tokenizer.from_pretrained("rjbownes/Magic-The-Generating")
model = GPT2LMHeadModel.from_pretrained("rjbownes/Magic-The-Generating")
```
#### Limitations and bias
The training corpus was surprisingly small, only ~29000 cards, I had suspected there were more. This might mean there is a real limit to the number of entirely original strings this will generate.
This is also only based on the 117M parameter GPT2, it's a pretty obvious upgrade to retrain with medium, large or XL models. However, despite this, the outputs I tested were very convincing!
## Training data
The data was 29222 MtG card flavour texts. The model was based on the "gpt2" pretrained transformer: https://huggingface.co/gpt2.
## Training procedure
Only English language MtG flavour texts were scraped from the [Scryfall](https://scryfall.com/) API. Empty strings and any non-UTF-8 encoded tokens were removed leaving 29222 entries.
This was trained using google Colab with a T4 instance. 4 epochs, adamW optimizer with default parameters and a batch size of 32. Token embedding lengths were capped at 98 tokens as this was the longest string and an attention mask was added to the training model to ignore all padding tokens.
## Eval results
Average Training Loss: 0.44866578806635815.
Validation loss: 0.5606984243444775.
Sample model outputs:
1. "Every branch a crossroads, every vine a swift steed."
—Gwendlyn Di Corci
2. "The secrets of this world will tell their masters where to strike if need be."
—Noyan Dar, Tazeem roilmage
3. "The secrets of nature are expensive. You'd be better off just to have more freedom."
4. "Even the Dwarves knew to leave some stones unturned."
5. "The wise always keep an ear open to the whispers of power."
### BibTeX entry and citation info
```bibtex
@article{BownesLM,
title={Fine Tuning GPT-2 for Magic the Gathering flavour text generation.},
author={Richard J. Bownes},
journal={Medium},
year={2020}
}
```
|
redrussianarmy/gpt2-turkish-cased
|
redrussianarmy
| 2021-05-23T12:12:42Z | 1,300 | 13 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"gpt2",
"text-generation",
"turkish",
"tr",
"gpt2-tr",
"gpt2-turkish",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: "tr"
tags:
- turkish
- tr
- gpt2-tr
- gpt2-turkish
---
# 🇹🇷 Turkish GPT-2 Model
In this repository I release GPT-2 model, that was trained on various texts for Turkish.
The model is meant to be an entry point for fine-tuning on other texts.
## Training corpora
I used a Turkish corpora that is taken from oscar-corpus.
It was possible to create byte-level BPE with Tokenizers library of Huggingface.
With the Tokenizers library, I created a 52K byte-level BPE vocab based on the training corpora.
After creating the vocab, I could train the GPT-2 for Turkish on two 2080TI over the complete training corpus (five epochs).
Logs during training:
https://tensorboard.dev/experiment/3AWKv8bBTaqcqZP5frtGkw/#scalars
## Model weights
Both PyTorch and Tensorflow compatible weights are available.
| Model | Downloads
| --------------------------------- | ---------------------------------------------------------------------------------------------------------------
| `redrussianarmy/gpt2-turkish-cased` | [`config.json`](https://huggingface.co/redrussianarmy/gpt2-turkish-cased/resolve/main/config.json) • [`merges.txt`](https://huggingface.co/redrussianarmy/gpt2-turkish-cased/resolve/main/merges.txt) • [`pytorch_model.bin`](https://huggingface.co/redrussianarmy/gpt2-turkish-cased/resolve/main/pytorch_model.bin) • [`special_tokens_map.json`](https://huggingface.co/redrussianarmy/gpt2-turkish-cased/resolve/main/special_tokens_map.json) • [`tf_model.h5`](https://huggingface.co/redrussianarmy/gpt2-turkish-cased/resolve/main/tf_model.h5) • [`tokenizer_config.json`](https://huggingface.co/redrussianarmy/gpt2-turkish-cased/resolve/main/tokenizer_config.json) • [`traning_args.bin`](https://huggingface.co/redrussianarmy/gpt2-turkish-cased/resolve/main/training_args.bin) • [`vocab.json`](https://huggingface.co/redrussianarmy/gpt2-turkish-cased/resolve/main/vocab.json)
## Using the model
The model itself can be used in this way:
``` python
from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained("redrussianarmy/gpt2-turkish-cased")
model = AutoModelWithLMHead.from_pretrained("redrussianarmy/gpt2-turkish-cased")
```
Here's an example that shows how to use the great Transformers Pipelines for generating text:
``` python
from transformers import pipeline
pipe = pipeline('text-generation', model="redrussianarmy/gpt2-turkish-cased",
tokenizer="redrussianarmy/gpt2-turkish-cased", config={'max_length':800})
text = pipe("Akşamüstü yolda ilerlerken, ")[0]["generated_text"]
print(text)
```
### How to clone the model repo?
```
git lfs install
git clone https://huggingface.co/redrussianarmy/gpt2-turkish-cased
```
## Contact (Bugs, Feedback, Contribution and more)
For questions about the GPT2-Turkish model, just open an issue [here](https://github.com/redrussianarmy/gpt2-turkish/issues) 🤗
|
himanshu-dutta/pycoder-gpt2
|
himanshu-dutta
| 2021-05-23T11:56:06Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
<br />
<div align="center">
<img src="https://raw.githubusercontent.com/himanshu-dutta/pycoder/master/docs/pycoder-logo-p.png">
<br/>
<img alt="Made With Python" src="http://ForTheBadge.com/images/badges/made-with-python.svg" height=28 style="display:inline; height:28px;" />
<img alt="Medium" src="https://img.shields.io/badge/Medium-12100E?style=for-the-badge&logo=medium&logoColor=white" height=28 style="display:inline; height:28px;"/>
<a href="https://wandb.ai/himanshu-dutta/pycoder">
<img alt="WandB Dashboard" src="https://raw.githubusercontent.com/wandb/assets/04cfa58cc59fb7807e0423187a18db0c7430bab5/wandb-github-badge-28.svg" height=28 style="display:inline; height:28px;" />
</a>
[](https://pypi.org/project/pycoder/)
</div>
<div align="justify">
`PyCoder` is a tool to generate python code out of a few given topics and a description. It uses GPT-2 language model as its engine. Pycoder poses writing Python code as a conditional-Causal Language Modelling(c-CLM). It has been trained on millions of lines of Python code written by all of us. At the current stage and state of training, it produces sensible code with few lines of description, but the scope of improvement for the model is limitless.
Pycoder has been developed as a Command-Line tool (CLI), an API endpoint, as well as a python package (yet to be deployed to PyPI). This repository acts as a framework for anyone who either wants to try to build Pycoder from scratch or turn Pycoder into maybe a `CPPCoder` or `JSCoder` 😃. A blog post about the development of the project will be released soon.
To use `Pycoder` as a CLI utility, clone the repository as normal, and install the package with:
```console
foo@bar:❯ pip install pycoder
```
After this the package could be verified and accessed as either a native CLI tool or a python package with:
```console
foo@bar:❯ python -m pycoder --version
Or directly as:
foo@bar:❯ pycoder --version
```
On installation the CLI can be used directly, such as:
```console
foo@bar:❯ pycoder -t pytorch -t torch -d "a trainer class to train vision model" -ml 120
```
The API endpoint is deployed using FastAPI. Once all the requirements have been installed for the project, the API can be accessed with:
```console
foo@bar:❯ pycoder --endpoint PORT_NUMBER
Or
foo@bar:❯ pycoder -e PORT_NUMBER
```
</div>
## Tech Stack
<div align="center">
<img alt="Python" src="https://img.shields.io/badge/python-%2314354C.svg?style=for-the-badge&logo=python&logoColor=white" style="display:inline;" />
<img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-%23EE4C2C.svg?style=for-the-badge&logo=PyTorch&logoColor=white" style="display:inline;" />
<img alt="Transformers" src="https://raw.githubusercontent.com/huggingface/transformers/master/docs/source/imgs/transformers_logo_name.png" height=28 width=120 style="display:inline; background-color:white; height:28px; width:120px"/>
<img alt="Docker" src="https://img.shields.io/badge/docker-%230db7ed.svg?style=for-the-badge&logo=docker&logoColor=white" style="display:inline;" />
<img src="https://fastapi.tiangolo.com/img/logo-margin/logo-teal.png" alt="FastAPI" height=28 style="display:inline; background-color:black; height:28px;" />
<img src="https://typer.tiangolo.com/img/logo-margin/logo-margin-vector.svg" height=28 style="display:inline; background-color:teal; height:28px;" />
</div>
## Tested Platforms
<div align="center">
<img alt="Linux" src="https://img.shields.io/badge/Linux-FCC624?style=for-the-badge&logo=linux&logoColor=black" style="display:inline;" />
<img alt="Windows 10" src="https://img.shields.io/badge/Windows-0078D6?style=for-the-badge&logo=windows&logoColor=white" style="display:inline;" />
</div>
## BibTeX
If you want to cite the framework feel free to use this:
```bibtex
@article{dutta2021pycoder,
title={Pycoder},
author={Dutta, H},
journal={GitHub. Note: https://github.com/himanshu-dutta/pycoder},
year={2021}
}
```
<hr />
<div align="center">
<img alt="MIT License" src="https://img.shields.io/github/license/himanshu-dutta/pycoder?style=for-the-badge&logo=appveyor" style="display:inline;" />
<img src="https://img.shields.io/badge/Copyright-Himanshu_Dutta-2ea44f?style=for-the-badge&logo=appveyor" style="display:inline;" />
</div>
|
pierreguillou/gpt2-small-portuguese
|
pierreguillou
| 2021-05-23T10:59:56Z | 45,373 | 44 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"gpt2",
"text-generation",
"pt",
"dataset:wikipedia",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: pt
widget:
- text: "Quem era Jim Henson? Jim Henson era um"
- text: "Em um achado chocante, o cientista descobriu um"
- text: "Barack Hussein Obama II, nascido em 4 de agosto de 1961, é"
- text: "Corrida por vacina contra Covid-19 já tem"
license: mit
datasets:
- wikipedia
---
# GPorTuguese-2: a Language Model for Portuguese text generation (and more NLP tasks...)
## Introduction
GPorTuguese-2 (Portuguese GPT-2 small) is a state-of-the-art language model for Portuguese based on the GPT-2 small model.
It was trained on Portuguese Wikipedia using **Transfer Learning and Fine-tuning techniques** in just over a day, on one GPU NVIDIA V100 32GB and with a little more than 1GB of training data.
It is a proof-of-concept that it is possible to get a state-of-the-art language model in any language with low ressources.
It was fine-tuned from the [English pre-trained GPT-2 small](https://huggingface.co/gpt2) using the Hugging Face libraries (Transformers and Tokenizers) wrapped into the [fastai v2](https://dev.fast.ai/) Deep Learning framework. All the fine-tuning fastai v2 techniques were used.
It is now available on Hugging Face. For further information or requests, please go to "[Faster than training from scratch — Fine-tuning the English GPT-2 in any language with Hugging Face and fastai v2 (practical case with Portuguese)](https://medium.com/@pierre_guillou/faster-than-training-from-scratch-fine-tuning-the-english-gpt-2-in-any-language-with-hugging-f2ec05c98787)".
## Model
| Model | #params | Model file (pt/tf) | Arch. | Training /Validation data (text) |
|-------------------------|---------|--------------------|-------------|------------------------------------------|
| `gpt2-small-portuguese` | 124M | 487M / 475M | GPT-2 small | Portuguese Wikipedia (1.28 GB / 0.32 GB) |
## Evaluation results
In a little more than a day (we only used one GPU NVIDIA V100 32GB; through a Distributed Data Parallel (DDP) training mode, we could have divided by three this time to 10 hours, just with 2 GPUs), we got a loss of 3.17, an **accuracy of 37.99%** and a **perplexity of 23.76** (see the validation results table below).
| after ... epochs | loss | accuracy (%) | perplexity | time by epoch | cumulative time |
|------------------|------|--------------|------------|---------------|-----------------|
| 0 | 9.95 | 9.90 | 20950.94 | 00:00:00 | 00:00:00 |
| 1 | 3.64 | 32.52 | 38.12 | 5:48:31 | 5:48:31 |
| 2 | 3.30 | 36.29 | 27.16 | 5:38:18 | 11:26:49 |
| 3 | 3.21 | 37.46 | 24.71 | 6:20:51 | 17:47:40 |
| 4 | 3.19 | 37.74 | 24.21 | 6:06:29 | 23:54:09 |
| 5 | 3.17 | 37.99 | 23.76 | 6:16:22 | 30:10:31 |
## GPT-2
*Note: information copied/pasted from [Model: gpt2 >> GPT-2](https://huggingface.co/gpt2#gpt-2)*
Pretrained model on English language using a causal language modeling (CLM) objective. It was introduced in this [paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) and first released at this [page](https://openai.com/blog/better-language-models/) (February 14, 2019).
Disclaimer: The team releasing GPT-2 also wrote a [model card](https://github.com/openai/gpt-2/blob/master/model_card.md) for their model. Content from this model card has been written by the Hugging Face team to complete the information they provided and give specific examples of bias.
## Model description
*Note: information copied/pasted from [Model: gpt2 >> Model description](https://huggingface.co/gpt2#model-description)*
GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was trained to guess the next word in sentences.
More precisely, inputs are sequences of continuous text of a certain length and the targets are the same sequence, shifted one token (word or piece of word) to the right. The model uses internally a mask-mechanism to make sure the predictions for the token `i` only uses the inputs from `1` to `i` but not the future tokens.
This way, the model learns an inner representation of the English language that can then be used to extract features useful for downstream tasks. The model is best at what it was pretrained for however, which is generating texts from a prompt.
## How to use GPorTuguese-2 with HuggingFace (PyTorch)
The following code use PyTorch. To use TensorFlow, check the below corresponding paragraph.
### Load GPorTuguese-2 and its sub-word tokenizer (Byte-level BPE)
```python
from transformers import AutoTokenizer, AutoModelWithLMHead
import torch
tokenizer = AutoTokenizer.from_pretrained("pierreguillou/gpt2-small-portuguese")
model = AutoModelWithLMHead.from_pretrained("pierreguillou/gpt2-small-portuguese")
# Get sequence length max of 1024
tokenizer.model_max_length=1024
model.eval() # disable dropout (or leave in train mode to finetune)
```
### Generate one word
```python
# input sequence
text = "Quem era Jim Henson? Jim Henson era um"
inputs = tokenizer(text, return_tensors="pt")
# model output
outputs = model(**inputs, labels=inputs["input_ids"])
loss, logits = outputs[:2]
predicted_index = torch.argmax(logits[0, -1, :]).item()
predicted_text = tokenizer.decode([predicted_index])
# results
print('input text:', text)
print('predicted text:', predicted_text)
# input text: Quem era Jim Henson? Jim Henson era um
# predicted text: homem
```
### Generate one full sequence
```python
# input sequence
text = "Quem era Jim Henson? Jim Henson era um"
inputs = tokenizer(text, return_tensors="pt")
# model output using Top-k sampling text generation method
sample_outputs = model.generate(inputs.input_ids,
pad_token_id=50256,
do_sample=True,
max_length=50, # put the token number you want
top_k=40,
num_return_sequences=1)
# generated sequence
for i, sample_output in enumerate(sample_outputs):
print(">> Generated text {}\n\n{}".format(i+1, tokenizer.decode(sample_output.tolist())))
# >> Generated text
# Quem era Jim Henson? Jim Henson era um executivo de televisão e diretor de um grande estúdio de cinema mudo chamado Selig,
# depois que o diretor de cinema mudo Georges Seuray dirigiu vários filmes para a Columbia e o estúdio.
```
## How to use GPorTuguese-2 with HuggingFace (TensorFlow)
The following code use TensorFlow. To use PyTorch, check the above corresponding paragraph.
### Load GPorTuguese-2 and its sub-word tokenizer (Byte-level BPE)
```python
from transformers import AutoTokenizer, TFAutoModelWithLMHead
import tensorflow as tf
tokenizer = AutoTokenizer.from_pretrained("pierreguillou/gpt2-small-portuguese")
model = TFAutoModelWithLMHead.from_pretrained("pierreguillou/gpt2-small-portuguese")
# Get sequence length max of 1024
tokenizer.model_max_length=1024
model.eval() # disable dropout (or leave in train mode to finetune)
```
### Generate one full sequence
```python
# input sequence
text = "Quem era Jim Henson? Jim Henson era um"
inputs = tokenizer.encode(text, return_tensors="tf")
# model output using Top-k sampling text generation method
outputs = model.generate(inputs, eos_token_id=50256, pad_token_id=50256,
do_sample=True,
max_length=40,
top_k=40)
print(tokenizer.decode(outputs[0]))
# >> Generated text
# Quem era Jim Henson? Jim Henson era um amigo familiar da família. Ele foi contratado pelo seu pai
# para trabalhar como aprendiz no escritório de um escritório de impressão, e então começou a ganhar dinheiro
```
## Limitations and bias
The training data used for this model come from Portuguese Wikipedia. We know it contains a lot of unfiltered content from the internet, which is far from neutral. As the openAI team themselves point out in their model card:
> Because large-scale language models like GPT-2 do not distinguish fact from fiction, we don’t support use-cases that require the generated text to be true. Additionally, language models like GPT-2 reflect the biases inherent to the systems they were trained on, so we do not recommend that they be deployed into systems that interact with humans > unless the deployers first carry out a study of biases relevant to the intended use-case. We found no statistically significant difference in gender, race, and religious bias probes between 774M and 1.5B, implying all versions of GPT-2 should be approached with similar levels of caution around use cases that are sensitive to biases around human attributes.
## Author
Portuguese GPT-2 small was trained and evaluated by [Pierre GUILLOU](https://www.linkedin.com/in/pierreguillou/) thanks to the computing power of the GPU (GPU NVIDIA V100 32 Go) of the [AI Lab](https://www.linkedin.com/company/ailab-unb/) (University of Brasilia) to which I am attached as an Associate Researcher in NLP and the participation of its directors in the definition of NLP strategy, Professors Fabricio Ataides Braz and Nilton Correia da Silva.
## Citation
If you use our work, please cite:
```bibtex
@inproceedings{pierre2020gpt2smallportuguese,
title={GPorTuguese-2 (Portuguese GPT-2 small): a Language Model for Portuguese text generation (and more NLP tasks...)},
author={Pierre Guillou},
year={2020}
}
```
|
pearsonkyle/gpt2-exomachina
|
pearsonkyle
| 2021-05-23T10:57:32Z | 7 | 1 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
# Exo-Machina
A deep language model, GPT-2, is trained on scientific manuscripts from NASA's Astrophysical Data System pertaining to extrasolar planets and the references therein. This pilot study uses the abstracts of each article as training data in order to explore correlations in scientific literature from a language perspective. A language model is a mathematical representation for an algorithm used to generate sequences in the same way a human would to form sentances. Each word or letter in a sentance is encoded to a numerical value (e.g. using word2vec) and is appended to a list forming sequences that represent up to a paragraph worth of text. The sequences are fed into the [GPT-2](https://openai.com/blog/better-language-models/) 117M model and trained for 500,000 steps with fine tuning. After training, the language model is used to generate new text from scratch and from user input.
- ### [Browse samples](https://pearsonkyle.github.io/Exo-Machina/)
- ### [Train a model on Google Colab](https://colab.research.google.com/drive/1Pur0rFi5YVdn7axYRacXWFMic4NxRexV?usp=sharing)
### Get started fast:
```python
from transformers import pipeline
exo = pipeline('text-generation',model='pearsonkyle/gpt2-exomachina', tokenizer='gpt2', config={'max_length':1600})
machina = lambda text: exo(text)[0]['generated_text']
print(machina("Transiting exoplanets are"))
```
## Training Samples
~40,000 Abstracts from NASA's Astrophysical data system (ADS) and ArXiv.
A few generated samples are below:
- *We can remotely sense an atmosphere by observing its reflected, transmitted, or emitted light in varying geometries. This light will contain information on the planetary conditions including* `temperature, pressure, composition, and cloud optical thickness. One such property that is important is...`
- *The reflectance of Earth's vegetation suggests*
`that large, deciduous forest fires are composed of mostly dry, unprocessed material that is distributed in a nearly patchy fashion. The distributions of these fires are correlated with temperature, and also with vegetation...`
- *Directly imaged exoplanets probe* `key aspects of planet formation and evolution theory, as well as atmospheric and interior physics. These insights have led to numerous direct imaging instruments for exoplanets, many using polarimetry. However, current instruments take`
Letting the scrape run for ~2 hours found articles from these publications:
```
5364 - The Astrophysical Journal
3365 - Astronomy and Astrophysics
2704 - Monthly Notices of the Royal Astronomical Society
1355 - The Astronomical Journal
617 - arXiv e-prints
498 - Icarus
388 - Publications of the Astronomical Society of the Pacific
324 - The Astrophysical Journal Supplement Series
245 - Nature
187 - Journal of Geophysical Research
167 - Science
145 - Astronomische Nachrichten
129 - Planetary and Space Science
114 - Space Science Reviews
109 - Geophysical Research Letters
```
|
p208p2002/gpt2-squad-qg-hl
|
p208p2002
| 2021-05-23T10:54:57Z | 13 | 3 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"question-generation",
"dataset:squad",
"arxiv:1606.05250",
"arxiv:1705.00106",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
datasets:
- squad
tags:
- question-generation
widget:
- text: "Harry Potter is a series of seven fantasy novels written by British author, [HL]J. K. Rowling[HL]."
---
# Transformer QG on SQuAD
HLQG is Proposed by [Ying-Hong Chan & Yao-Chung Fan. (2019). A Re-current BERT-based Model for Question Generation.](https://www.aclweb.org/anthology/D19-5821/)
**This is a Reproduce Version**
More detail: [p208p2002/Transformer-QG-on-SQuAD](https://github.com/p208p2002/Transformer-QG-on-SQuAD)
## Usage
### Input Format
```
C' = [c1, c2, ..., [HL], a1, ..., a|A|, [HL], ..., c|C|]
```
### Input Example
```
Harry Potter is a series of seven fantasy novels written by British author, [HL]J. K. Rowling[HL].
```
> # Who wrote Harry Potter?
## Data setting
We report two dataset setting as Follow
### SQuAD
- train: 87599\\\\t
- validation: 10570
> [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://arxiv.org/abs/1606.05250)
### SQuAD NQG
- train: 75722
- dev: 10570
- test: 11877
> [Learning to Ask: Neural Question Generation for Reading Comprehension](https://arxiv.org/abs/1705.00106)
## Available models
- BART
- GPT2
- T5
## Expriments
We report score with `NQG Scorer` which is using in SQuAD NQG.
If not special explanation, the size of the model defaults to "base".
### SQuAD
Model |Bleu 1|Bleu 2|Bleu 3|Bleu 4|METEOR|ROUGE-L|
---------------------------------|------|------|------|------|------|-------|
BART-HLSQG |54.67 |39.26 |30.34 |24.15 |25.43 |52.64 |
GPT2-HLSQG |49.31 |33.95 |25.41| 19.69 |22.29 |48.82 |
T5-HLSQG |54.29 |39.22 |30.43 |24.26 |25.56 |53.11 |
### SQuAD NQG
Model |Bleu 1|Bleu 2|Bleu 3|Bleu 4|METEOR|ROUGE-L|
---------------------------------|------|------|------|------|------|-------|
BERT-HLSQG (Chan et al.) |49.73 |34.60 |26.13 |20.33 |23.88 |48.23 |
BART-HLSQG |54.12 |38.19 |28.84 |22.35 |24.55 |51.03 |
GPT2-HLSQG |49.82 |33.69 |24.71 |18.63 |21.90 |47.60 |
T5-HLSQG |53.13 |37.60 |28.62 |22.38 |24.48 |51.20 |
|
ncoop57/DiGPTame-medium
|
ncoop57
| 2021-05-23T10:47:17Z | 37 | 2 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"conversational",
"arxiv:1911.00536",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
tags:
- conversational
license: mit
---
## Finetuned DialoGPT model on Spanish Conversations
This model was finetuned from the original [DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium) model on subtitles from Spanish movies and telenovelas from the awesome [OpenSubtitle dataset](https://github.com/PolyAI-LDN/conversational-datasets/tree/master/opensubtitles).
DialoGPT paper: [https://arxiv.org/abs/1911.00536](https://arxiv.org/abs/1911.00536)
Some example dialog from the model:
|Role | Response |
|---------|--------|
|User | ¿Cómo está el clima hoy? |
| Bot | Muy bien. |
|User | Eso es bueno escuchar. ¿Vas a ir a la playa? |
| Bot | No, también puedo regresar. |
|User | Oh bien, bueno, iré a la playa más tarde. |
| Bot | ¡No! |
|User | ¿Qué está mal con eso? |
| Bot | ¡Cómo que no! |
|User | Estoy confundido, ¿por qué no puedo ir a la playa? |
| Bot | ¡Cómo que no! |
|User | Explícamelo por favor. |
| Bot | ¡No! |
## 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("ncoop57/DiGPTame-medium")
model = AutoModelWithLMHead.from_pretrained("ncoop57/DiGPTame-medium")
# 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)))
```
## Training your own model
If you would like to finetune your own model or finetune this Spanish model, please checkout my blog post on that exact topic!
https://nathancooper.io/i-am-a-nerd/chatbot/deep-learning/gpt2/2020/05/12/chatbot-part-1.html
|
mymusise/EasternFantasyNoval-small
|
mymusise
| 2021-05-23T10:41:05Z | 7 | 1 |
transformers
|
[
"transformers",
"tf",
"gpt2",
"text-generation",
"zh",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: zh
widget:
- text: "今天是下雨天"
- text: "走向森林"
---
# EasternFantasyNoval
# Overview
- **Language model**: GPT2-Medium
- **Model size**: 1.2GiB
- **Language**: Chinese
|
mrm8488/gpt2-imdb-neg
|
mrm8488
| 2021-05-23T10:27:14Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | null | 2022-03-02T23:29:05Z |
# GPT2-IMDB-neg (LM + RL) 🎞😡✍
All credits to [@lvwerra](https://twitter.com/lvwerra)
## What is it?
A small GPT2 (`lvwerra/gpt2-imdb`) language model fine-tuned to produce **negative** movie reviews based the [IMDB dataset](https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews). The model is trained with rewards from a BERT sentiment classifier (`lvwerra/gpt2-imdb`) via **PPO**.
## Why?
I wanted to reproduce the experiment [lvwerra/gpt2-imdb-pos](https://huggingface.co/lvwerra/gpt2-imdb-pos) but for generating **negative** movie reviews.
## Training setting
The model was trained for `100` optimisation steps with a batch size of `256` which corresponds to `25600` training samples. The full experiment setup (for positive samples) in [trl repo](https://lvwerra.github.io/trl/04-gpt2-sentiment-ppo-training/).
## Examples
A few examples of the model response to a query before and after optimisation:
| query | response (before) | response (after) | rewards (before) | rewards (after) |
|-------|-------------------|------------------|------------------|-----------------|
|This movie is a fine | attempt as far as live action is concerned, n...|example of how bad Hollywood in theatrics pla...| 2.118391 | -3.31625|
|I have watched 3 episodes |with this guy and he is such a talented actor...| but the show is just plain awful and there ne...| 2.681171| -4.512792|
|We know that firefighters and| police officers are forced to become populari...| other chains have going to get this disaster ...| 1.367811| -3.34017|
## Training logs and metrics <img src="https://gblobscdn.gitbook.com/spaces%2F-Lqya5RvLedGEWPhtkjU%2Favatar.png?alt=media" width="25" height="25">
Watch the whole training logs and metrics on [W&B](https://app.wandb.ai/mrm8488/gpt2-sentiment-negative?workspace=user-mrm8488)
> Created by [Manuel Romero/@mrm8488](https://twitter.com/mrm8488)
> Made with <span style="color: #e25555;">♥</span> in Spain
|
mrm8488/distilgpt2-finetuned-wsb-tweets
|
mrm8488
| 2021-05-23T10:23:17Z | 14 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"wsb",
"tweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
tags:
- wsb
- tweets
widget:
- text: "Come on guys this is"
---
# distilGPT-2 fine-tuned on Kaggle WSB Reddit posts dataset
|
mrm8488/GuaPeTe-2-tiny-finetuned-eubookshop
|
mrm8488
| 2021-05-23T10:15:52Z | 11 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"spanish",
"gpt-2",
"es",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: es
tags:
- spanish
- gpt-2
widget:
- text: "El objetivo de la Unión Europea es"
---
# GuaPeTe-2-tiny fine-tuned on eubookshop dataset for CLM
|
mrm8488/GPT-2-finetuned-common_gen
|
mrm8488
| 2021-05-23T10:12:07Z | 135 | 3 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"en",
"dataset:common_gen",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
datasets:
- common_gen
widget:
- text: "<|endoftext|> apple, tree, pick:"
---
# GPT-2 fine-tuned on CommonGen
[GPT-2](https://huggingface.co/gpt2) fine-tuned on [CommonGen](https://inklab.usc.edu/CommonGen/index.html) for *Generative Commonsense Reasoning*.
## Details of GPT-2
GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This
means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots
of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely,
it was trained to guess the next word in sentences.
More precisely, inputs are sequences of continuous text of a certain length and the targets are the same sequence,
shifted one token (word or piece of word) to the right. The model uses internally a mask-mechanism to make sure the
predictions for the token `i` only uses the inputs from `1` to `i` but not the future tokens.
This way, the model learns an inner representation of the English language that can then be used to extract features
useful for downstream tasks. The model is best at what it was pretrained for however, which is generating texts from a
prompt.
## Details of the dataset 📚
CommonGen is a constrained text generation task, associated with a benchmark dataset, to explicitly test machines for the ability of generative commonsense reasoning. Given a set of common concepts; the task is to generate a coherent sentence describing an everyday scenario using these concepts.
CommonGen is challenging because it inherently requires 1) relational reasoning using background commonsense knowledge, and 2) compositional generalization ability to work on unseen concept combinations. Our dataset, constructed through a combination of crowd-sourcing from AMT and existing caption corpora, consists of 30k concept-sets and 50k sentences in total.
| Dataset | Split | # samples |
| -------- | ----- | --------- |
| common_gen | train | 67389 |
| common_gen | valid | 4018 |
| common_gen | test | 1497 |
## Model fine-tuning 🏋️
You can find the fine-tuning script [here](https://github.com/huggingface/transformers/tree/master/examples/language-modeling)
## Model in Action 🚀
```bash
python ./transformers/examples/text-generation/run_generation.py \
--model_type=gpt2 \
--model_name_or_path="mrm8488/GPT-2-finetuned-common_gen" \
--num_return_sequences 1 \
--prompt "<|endoftext|> kid, room, dance:" \
--stop_token "."
```
> Created by [Manuel Romero/@mrm8488](https://twitter.com/mrm8488) | [LinkedIn](https://www.linkedin.com/in/manuel-romero-cs/)
> Made with <span style="color: #e25555;">♥</span> in Spain
|
mofawzy/gpt-2-goodreads-ar
|
mofawzy
| 2021-05-23T09:53:17Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
### Generate Arabic reviews sentences with model GPT-2 Medium.
#### Load model
```
from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained("mofawzy/gpt-2-medium-ar")
model = AutoModelWithLMHead.from_pretrained("mofawzy/gpt-2-medium-ar")
```
### Eval:
```
***** eval metrics *****
epoch = 20.0
eval_loss = 1.7798
eval_mem_cpu_alloc_delta = 3MB
eval_mem_cpu_peaked_delta = 0MB
eval_mem_gpu_alloc_delta = 0MB
eval_mem_gpu_peaked_delta = 7044MB
eval_runtime = 0:03:03.37
eval_samples = 527
eval_samples_per_second = 2.874
perplexity = 5.9285
```
#### Notebook:
https://colab.research.google.com/drive/1P0Raqrq0iBLNH87DyN9j0SwWg4C2HubV?usp=sharing
|
microsoft/DialogRPT-width
|
microsoft
| 2021-05-23T09:20:20Z | 41 | 1 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-classification",
"arxiv:2009.06978",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2022-03-02T23:29:05Z |
# Demo
Please try this [➤➤➤ Colab Notebook Demo (click me!)](https://colab.research.google.com/drive/1cAtfkbhqsRsT59y3imjR1APw3MHDMkuV?usp=sharing)
| Context | Response | `width` score |
| :------ | :------- | :------------: |
| I love NLP! | Can anyone recommend a nice review paper? | 0.701 |
| I love NLP! | Me too! | 0.029 |
The `width` score predicts how likely the response is getting replied.
# DialogRPT-width
### Dialog Ranking Pretrained Transformers
> How likely a dialog response is upvoted 👍 and/or gets replied 💬?
This is what [**DialogRPT**](https://github.com/golsun/DialogRPT) is learned to predict.
It is a set of dialog response ranking models proposed by [Microsoft Research NLP Group](https://www.microsoft.com/en-us/research/group/natural-language-processing/) trained on 100 + millions of human feedback data.
It can be used to improve existing dialog generation model (e.g., [DialoGPT](https://huggingface.co/microsoft/DialoGPT-medium)) by re-ranking the generated response candidates.
Quick Links:
* [EMNLP'20 Paper](https://arxiv.org/abs/2009.06978/)
* [Dataset, training, and evaluation](https://github.com/golsun/DialogRPT)
* [Colab Notebook Demo](https://colab.research.google.com/drive/1cAtfkbhqsRsT59y3imjR1APw3MHDMkuV?usp=sharing)
We considered the following tasks and provided corresponding pretrained models.
|Task | Description | Pretrained model |
| :------------- | :----------- | :-----------: |
| **Human feedback** | **given a context and its two human responses, predict...**|
| `updown` | ... which gets more upvotes? | [model card](https://huggingface.co/microsoft/DialogRPT-updown) |
| `width`| ... which gets more direct replies? | this model |
| `depth`| ... which gets longer follow-up thread? | [model card](https://huggingface.co/microsoft/DialogRPT-depth) |
| **Human-like** (human vs fake) | **given a context and one human response, distinguish it with...** |
| `human_vs_rand`| ... a random human response | [model card](https://huggingface.co/microsoft/DialogRPT-human-vs-rand) |
| `human_vs_machine`| ... a machine generated response | [model card](https://huggingface.co/microsoft/DialogRPT-human-vs-machine) |
### Contact:
Please create an issue on [our repo](https://github.com/golsun/DialogRPT)
### Citation:
```
@inproceedings{gao2020dialogrpt,
title={Dialogue Response RankingTraining with Large-Scale Human Feedback Data},
author={Xiang Gao and Yizhe Zhang and Michel Galley and Chris Brockett and Bill Dolan},
year={2020},
booktitle={EMNLP}
}
```
|
microsoft/DialogRPT-human-vs-rand
|
microsoft
| 2021-05-23T09:18:07Z | 36 | 9 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-classification",
"arxiv:2009.06978",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2022-03-02T23:29:05Z |
# Demo
Please try this [➤➤➤ Colab Notebook Demo (click me!)](https://colab.research.google.com/drive/1cAtfkbhqsRsT59y3imjR1APw3MHDMkuV?usp=sharing)
| Context | Response | `human_vs_rand` score |
| :------ | :------- | :------------: |
| I love NLP! | He is a great basketball player. | 0.027 |
| I love NLP! | Can you tell me how it works? | 0.754 |
| I love NLP! | Me too! | 0.631 |
The `human_vs_rand` score predicts how likely the response is corresponding to the given context, rather than a random response.
# DialogRPT-human-vs-rand
### Dialog Ranking Pretrained Transformers
> How likely a dialog response is upvoted 👍 and/or gets replied 💬?
This is what [**DialogRPT**](https://github.com/golsun/DialogRPT) is learned to predict.
It is a set of dialog response ranking models proposed by [Microsoft Research NLP Group](https://www.microsoft.com/en-us/research/group/natural-language-processing/) trained on 100 + millions of human feedback data.
It can be used to improve existing dialog generation model (e.g., [DialoGPT](https://huggingface.co/microsoft/DialoGPT-medium)) by re-ranking the generated response candidates.
Quick Links:
* [EMNLP'20 Paper](https://arxiv.org/abs/2009.06978/)
* [Dataset, training, and evaluation](https://github.com/golsun/DialogRPT)
* [Colab Notebook Demo](https://colab.research.google.com/drive/1cAtfkbhqsRsT59y3imjR1APw3MHDMkuV?usp=sharing)
We considered the following tasks and provided corresponding pretrained models.
|Task | Description | Pretrained model |
| :------------- | :----------- | :-----------: |
| **Human feedback** | **given a context and its two human responses, predict...**|
| `updown` | ... which gets more upvotes? | [model card](https://huggingface.co/microsoft/DialogRPT-updown) |
| `width`| ... which gets more direct replies? | [model card](https://huggingface.co/microsoft/DialogRPT-width) |
| `depth`| ... which gets longer follow-up thread? | [model card](https://huggingface.co/microsoft/DialogRPT-depth) |
| **Human-like** (human vs fake) | **given a context and one human response, distinguish it with...** |
| `human_vs_rand`| ... a random human response | this model |
| `human_vs_machine`| ... a machine generated response | [model card](https://huggingface.co/microsoft/DialogRPT-human-vs-machine) |
### Contact:
Please create an issue on [our repo](https://github.com/golsun/DialogRPT)
### Citation:
```
@inproceedings{gao2020dialogrpt,
title={Dialogue Response RankingTraining with Large-Scale Human Feedback Data},
author={Xiang Gao and Yizhe Zhang and Michel Galley and Chris Brockett and Bill Dolan},
year={2020},
booktitle={EMNLP}
}
```
|
manav/dialogpt-medium-berkeley-reddit
|
manav
| 2021-05-23T08:52:16Z | 7 | 1 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"conversational",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
tags:
- conversational
---
## Model description
Finetuned version of DialogPT-medium released. Finetuned on data scraped from the r/Berkeley subreddit. The data wasn't thoroughly vetted so the model may display biases that I am unaware of, so tread with caution when this model until further analysis of its biases can be performed.
|
lysandre/arxiv
|
lysandre
| 2021-05-23T08:44:27Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | null | 2022-03-02T23:29:05Z |
# ArXiv GPT-2 checkpoint
This is a GPT-2 small checkpoint for PyTorch. It is the official `gpt2-small` finetuned to ArXiv paper on physics fields.
## Training data
This model was trained on a subset of ArXiv papers that were parsed from PDF to txt. The resulting data is made of 130MB of text, mostly from quantum physics (quant-ph) and other physics sub-fields.
|
lvwerra/gpt2-medium-taboo
|
lvwerra
| 2021-05-23T08:40:35Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
# GPT-2 (medium) Taboo
## What is it?
A fine-tuned GPT-2 version for Taboo cards generation.
## Training setting
The model was trained on ~900 Taboo cards in the following format for 100 epochs:
```
Describe the word Glitch without using the words Problem, Unexpected, Technology, Minor, Outage.
````
|
lvwerra/gpt2-imdb
|
lvwerra
| 2021-05-23T08:38:34Z | 44,499 | 16 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
# GPT2-IMDB
## What is it?
A GPT2 (`gpt2`) language model fine-tuned on the [IMDB dataset](https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews).
## Training setting
The GPT2 language model was fine-tuned for 1 epoch on the IMDB dataset. All comments were joined into a single text file separated by the EOS token:
```
import pandas as pd
df = pd.read_csv("imdb-dataset.csv")
imdb_str = " <|endoftext|> ".join(df['review'].tolist())
with open ('imdb.txt', 'w') as f:
f.write(imdb_str)
```
To train the model the `run_language_modeling.py` script in the `transformer` library was used:
```
python run_language_modeling.py
--train_data_file imdb.txt
--output_dir gpt2-imdb
--model_type gpt2
--model_name_or_path gpt2
```
|
lvwerra/gpt2-imdb-ctrl
|
lvwerra
| 2021-05-23T08:37:09Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | null | 2022-03-02T23:29:05Z |
# GPT2-IMDB-ctrl
## What is it?
A small GPT2 (`lvwerra/gpt2-imdb`) language model fine-tuned to produce controlled movie reviews based the [IMDB dataset](https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews). The model is trained with rewards from a BERT sentiment classifier (`lvwerra/bert-imdb`) via PPO.
## Training setting
The model was trained for `200` optimisation steps with a batch size of `256` which corresponds to `51200` training samples. The full experiment setup can be found in the Jupyter notebook in the [trl repo](https://lvwerra.github.io/trl/05-gpt2-sentiment-ppo-training/). The strings `"[negative]"`, `"[neutral]"`, and `"[positive]"` are added at the beginning of the query to control the sentiment.
## Examples
A few examples of the model response to a query before and after optimisation:
| query | response [negative] | rewards [negative] | response [neutral] | rewards [neutral] | response [positive] | rewards [positive] |
|-------|---------------------|--------------------|--------------------|-------------------|---------------------|--------------------|
|I watched this movie when|it was released and was awful. Little bit of ...|3.130034|it was released and it was the first movie I ...|-1.351991|I was younger it was wonderful. The new play ...|4.232218|
|I can remember seeing this|movie in 2008, and I was so disappointed...yo...|3.428725|in support groups, which I think was not as i...|0.213288|movie, and it is one of my favorite movies ev...|4.168838|
|This 1970 hit film has|little resonance. This movie is bad, not only...|4.241872|a bit of Rocket power.783287. It can be easil...|0.849278|the best formula for comedy and is't just jus...|4.208804|
|
lighteternal/gpt2-finetuned-greek-small
|
lighteternal
| 2021-05-23T08:32:03Z | 25 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"causal-lm",
"el",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language:
- el
tags:
- pytorch
- causal-lm
widget:
- text: "Το αγαπημένο μου μέρος είναι"
license: apache-2.0
---
# Greek (el) GPT2 model - small
<img src="https://huggingface.co/lighteternal/gpt2-finetuned-greek-small/raw/main/GPT2el.png" width="600"/>
#### A new version (recommended) trained on 5x more data is available at: https://huggingface.co/lighteternal/gpt2-finetuned-greek
### By the Hellenic Army Academy (SSE) and the Technical University of Crete (TUC)
* language: el
* licence: apache-2.0
* dataset: ~5GB of Greek corpora
* model: GPT2 (12-layer, 768-hidden, 12-heads, 117M parameters. OpenAI GPT-2 English model, finetuned for the Greek language)
* pre-processing: tokenization + BPE segmentation
### Model description
A text generation (autoregressive) model, using Huggingface transformers and fastai based on the English GPT-2(small). 

Finetuned with gradual layer unfreezing. This is a more efficient and sustainable alternative compared to training from scratch, especially for low-resource languages. 

Based on the work of Thomas Dehaene (ML6) for the creation of a Dutch GPT2: https://colab.research.google.com/drive/1Y31tjMkB8TqKKFlZ5OJ9fcMp3p8suvs4?usp=sharing
### How to use
```
from transformers import pipeline
model = "lighteternal/gpt2-finetuned-greek-small"
generator = pipeline(
'text-generation',
device=0,
model=f'{model}',
tokenizer=f'{model}')
text = "Μια φορά κι έναν καιρό"
print("\\\\
".join([x.get("generated_text") for x in generator(
text,
max_length=len(text.split(" "))+15,
do_sample=True,
top_k=50,
repetition_penalty = 1.2,
add_special_tokens=False,
num_return_sequences=5,
temperature=0.95,
top_p=0.95)]))
```
## Training data
We used a small (~5GB) sample from a consolidated Greek corpus based on CC100, Wikimatrix, Tatoeba, Books, SETIMES and GlobalVoices. A bigger corpus is expected to provide better results (T0D0).
### Acknowledgement
The research work was supported by the Hellenic Foundation for Research and Innovation (HFRI) under the HFRI PhD Fellowship grant (Fellowship Number:50, 2nd call)
Based on the work of Thomas Dehaene (ML6): https://blog.ml6.eu/dutch-gpt2-autoregressive-language-modelling-on-a-budget-cff3942dd020
|
A-bhimany-u08/bert-base-cased-qqp
|
A-bhimany-u08
| 2021-05-23T06:58:51Z | 29 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"dataset:qqp",
"autotrain_compatible",
"region:us"
] |
text-classification
| 2022-03-02T23:29:04Z |
---
inference: False
datasets:
- qqp
---
bert-base-cased model trained on quora question pair dataset. The task requires to predict whether the two given sentences (or questions) are `not_duplicate` (label 0) or `duplicate` (label 1). The model achieves 89% evaluation accuracy
|
ktrapeznikov/gpt2-medium-topic-small-set
|
ktrapeznikov
| 2021-05-23T06:21:38Z | 7 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language:
- en
thumbnail:
widget:
- text: "topic climate source"
---
# GPT2-medium-topic-news
## Model description
GPT2-medium fine tuned on a small news corpus conditioned on a topic, source, title
## Intended uses & limitations
#### How to use
To generate a news article text conditioned on a topic, source, title or some subsets, prompt model with:
```python
f"topic {topic} source"
f"topic {topic} source {source} title"
f"topic {topic} source {source} title {title} body"
```
Try the following tags for `topic: climate, weather, vaccination`.
Zero shot generation works pretty well as long as `topic` is a single word and not too specific.
```python
device = "cuda:0"
tokenizer = AutoTokenizer.from_pretrained("ktrapeznikov/gpt2-medium-topic-small-set")
model = AutoModelWithLMHead.from_pretrained("ktrapeznikov/gpt2-medium-topic-small-set")
model.to(device)
topic = "climate"
prompt = tokenizer(f"topic {topics} source straitstimes title", return_tensors="pt")
out = model.generate(prompt["input_ids"].to(device), do_sample=True,max_length=500, early_stopping=True, top_p=.9)
print(tokenizer.decode(out[0].cpu(), skip_special_tokens=True))
```
## Sample Output
>[topic] military [source] straitstimes [title] Trump signs bill on military aid to Israel [body] WASHINGTON (AFP) - US President Donald Trump signed into law Thursday (April 24) legislation to provide more than US$15 billion (S$20.43 billion) in military aid to Israel, a move the Obama administration had resisted for political reasons. The White House did not immediately respond to a request for comment on the Israel measure, which Trump had sought unsuccessfully to block during the Obama pres ...
>[topic] military [source] straitstimes [title] Hong Kong's leaders to discuss new travel restrictions as lockdown looms [body] HONG KONG (REUTERS) - Hong Kong authorities said they would hold a meeting of the Legislative Council on Monday (July 21) to discuss new travel restrictions on Hong Kong residents, as the city reported a record daily increase in coronavirus cases. The authorities said they would consider the proposal after meeting government chiefs and reviewing other measures. The co ...
>[topic] military [source] straitstimes [title] Trump signs Bill that gives US troops wider latitude to conduct operations abroad [body] WASHINGTON (AFP) - US President Donald Trump on Thursday (July 23) signed a controversial law that gives US troops more leeway to conduct operations abroad, as he seeks to shore up the embattled government's defences against the coronavirus pandemic and stave off a potentially devastating election defeat. Trump's signature Bill, named after his late father's l ...
>[topic] military [source] straitstimes [title] China's Foreign Ministry responds to Japan's statement on South China Sea: 'No one should assume the role of mediator' [body] BEIJING (AFP) - The Ministry of Foreign Affairs on Tuesday (Oct 18) told Japan to stop taking sides in the South China Sea issue and not interfere in the bilateral relationship, as Japan said it would do "nothing". Foreign Ministry spokesman Zhao Lijian told reporters in Beijing that the Chinese government's position on the ...
>[topic] military [source] straitstimes [title] US warns North Korea on potential nuclear strike [body] WASHINGTON - The United States warned North Korea last Friday that an attack by the North could be a "provocation" that would have "a devastating effect" on its security, as it took aim at Pyongyang over its continued efforts to develop weapons of mass destruction. US Secretary of State Mike Pompeo was speaking at the conclusion of a White House news conference when a reporter asked him how t ...
>[topic] military [source] straitstimes [title] China calls Hong Kong to halt 'illegal and illegal military acts' [body] WASHINGTON • Chinese Foreign Ministry spokeswoman Hua Chunying said yesterday that Hong Kong must stop 'illegal and illegal military acts' before Beijing can recognise the city as its own. In her annual State Councillor's speech, Ms Hua made the case for Hong Kong to resume Hong Kong's status as a semi-autonomous city, and vowed to use its "great power position to actively an ...
## Training data
## Training procedure
|
kiri-ai/gpt2-large-quantized
|
kiri-ai
| 2021-05-23T06:13:04Z | 14 | 0 |
transformers
|
[
"transformers",
"gpt2",
"text-generation",
"en",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language:
- en
---
# Pytorch int8 quantized version of gpt2-large
## Usage
Download the .bin file locally.
Load with:
Rest of the usage according to [original instructions](https://huggingface.co/gpt2-large).
```python
import torch
model = torch.load("path/to/pytorch_model_quantized.bin")
```
|
huggingtweets/zrkrlc
|
huggingtweets
| 2021-05-23T05:26:40Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/zrkrlc/1616626091555/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1332547297914175494/RAz44L4J_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">object-level jail 🚨 🤖 AI Bot </div>
<div style="font-size: 15px">@zrkrlc bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@zrkrlc's tweets](https://twitter.com/zrkrlc).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 2241 |
| Retweets | 228 |
| Short tweets | 204 |
| Tweets kept | 1809 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2g51am53/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @zrkrlc's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/23unb7ar) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/23unb7ar/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/zrkrlc')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/zlisto
|
huggingtweets
| 2021-05-23T05:24:22Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/zlisto/1611290409885/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/933754221257723904/OPVfNgZG_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Tauhid R. Zaman 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@zlisto bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@zlisto's tweets](https://twitter.com/zlisto).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>3157</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>1202</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>117</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>1838</td>
</tr>
</tbody>
</table>
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3p8ylpjm/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @zlisto's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/220gmo20) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/220gmo20/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/zlisto'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/zachfox
|
huggingtweets
| 2021-05-23T05:13:41Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/zachfox/1603321719549/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1142440824766193664/6NK0B-Gr_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Zach Fox 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@zachfox bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@zachfox's tweets](https://twitter.com/zachfox).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>3168</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>547</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>415</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>2206</td>
</tr>
</tbody>
</table>
[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/21svlsaa/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @zachfox's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/21o6mb7e) for full transparency and reproducibility.
At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/21o6mb7e/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/zachfox'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
<!--- random size file -->
|
huggingtweets/zacharyhundley
|
huggingtweets
| 2021-05-23T05:12:24Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/zacharyhundley/1616620657215/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1336547084372234241/ZthomfiN_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Zachary 💻🖱️ 🤖 AI Bot </div>
<div style="font-size: 15px">@zacharyhundley bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@zacharyhundley's tweets](https://twitter.com/zacharyhundley).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3246 |
| Retweets | 260 |
| Short tweets | 797 |
| Tweets kept | 2189 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2d5adsoe/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @zacharyhundley's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/ni6yl621) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/ni6yl621/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/zacharyhundley')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/yujiri3
|
huggingtweets
| 2021-05-23T05:05:22Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/yujiri3/1616651697285/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1350388215975456768/hyUBufqg_400x400.png')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Yujiri (my likes don't always work) 🤖 AI Bot </div>
<div style="font-size: 15px">@yujiri3 bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@yujiri3's tweets](https://twitter.com/yujiri3).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3182 |
| Retweets | 773 |
| Short tweets | 318 |
| Tweets kept | 2091 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/353ok7f3/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @yujiri3's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/sqw7eetr) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/sqw7eetr/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/yujiri3')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/yellowdogedem
|
huggingtweets
| 2021-05-23T04:59:31Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/yellowdogedem/1617172947443/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1374515470498373639/dygzoNob_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Toby (Inactive) 🗳️🥑⚙️🚊🌃🚀🌐 🤖 AI Bot </div>
<div style="font-size: 15px">@yellowdogedem bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@yellowdogedem's tweets](https://twitter.com/yellowdogedem).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3233 |
| Retweets | 494 |
| Short tweets | 788 |
| Tweets kept | 1951 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2ln60y7n/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @yellowdogedem's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2vj8xb46) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2vj8xb46/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/yellowdogedem')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/xescobin
|
huggingtweets
| 2021-05-23T04:49:24Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/xescobin/1608382856568/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1322124437039165442/wNDVA07K_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">xean 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@xescobin bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@xescobin's tweets](https://twitter.com/xescobin).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>848</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>51</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>213</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>584</td>
</tr>
</tbody>
</table>
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3tc2mjf0/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @xescobin's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2gvtor1n) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2gvtor1n/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/xescobin'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/wyattpuppers
|
huggingtweets
| 2021-05-23T04:47:07Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/wyattpuppers/1609011422698/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1340068830673027074/VVV2NNgn_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">C a r p 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@wyattpuppers bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@wyattpuppers's tweets](https://twitter.com/wyattpuppers).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>3190</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>478</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>481</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>2231</td>
</tr>
</tbody>
</table>
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1bl7smzv/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @wyattpuppers's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/ld6fkx1k) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/ld6fkx1k/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/wyattpuppers'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/wrathofgnon
|
huggingtweets
| 2021-05-23T04:41:01Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/wrathofgnon/1603923813760/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/939424471353475072/fB-3BRin_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Wrath Of Gnon 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@wrathofgnon bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@wrathofgnon's tweets](https://twitter.com/wrathofgnon).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>3227</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>499</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>116</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>2612</td>
</tr>
</tbody>
</table>
[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/x0tn1ht9/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @wrathofgnon's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/39eutbnd) for full transparency and reproducibility.
At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/39eutbnd/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/wrathofgnon'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
<!--- random size file -->
|
huggingtweets/worrski_
|
huggingtweets
| 2021-05-23T04:38:29Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/worrski_/1616131395706/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1370683624324956162/R6cB17BK_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">21st Century Schizoid Ben 🤖 AI Bot </div>
<div style="font-size: 15px">@worrski_ bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@worrski_'s tweets](https://twitter.com/worrski_).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3190 |
| Retweets | 531 |
| Short tweets | 856 |
| Tweets kept | 1803 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1g9vvlkk/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @worrski_'s tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/17oq1dis) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/17oq1dis/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/worrski_')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/woketopus
|
huggingtweets
| 2021-05-23T04:33:18Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/woketopus/1614149251542/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1363814877119336451/DtC1OuMG_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">woketopus is grooving 🤖 AI Bot </div>
<div style="font-size: 15px">@woketopus bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@woketopus's tweets](https://twitter.com/woketopus).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3219 |
| Retweets | 217 |
| Short tweets | 646 |
| Tweets kept | 2356 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3t0s1gfu/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @woketopus's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1s4xkpp2) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1s4xkpp2/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/woketopus')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/witten271
|
huggingtweets
| 2021-05-23T04:32:11Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('http://pbs.twimg.com/profile_images/1264681056256565268/lrwZRqIv_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Edward Witten 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@witten271 bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@witten271's tweets](https://twitter.com/witten271).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>1337</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>761</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>32</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>544</td>
</tr>
</tbody>
</table>
[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/i5o4s13a/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @witten271's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/35w4smrg) for full transparency and reproducibility.
At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/35w4smrg/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/witten271'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/witchdagguh
|
huggingtweets
| 2021-05-23T04:31:08Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/witchdagguh/1614138864003/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1184495597967106049/BPXCzXkd_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Chaotic Maelstrom of Willing Hands 🤖 AI Bot </div>
<div style="font-size: 15px">@witchdagguh bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@witchdagguh's tweets](https://twitter.com/witchdagguh).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3046 |
| Retweets | 1626 |
| Short tweets | 135 |
| Tweets kept | 1285 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1tqwxgqa/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @witchdagguh's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3ng9fmxq) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3ng9fmxq/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/witchdagguh')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/wired
|
huggingtweets
| 2021-05-23T04:29:56Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/wired/1601263431883/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1228050699348561920/YvWAQD2L_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">WIRED 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@wired bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@wired's tweets](https://twitter.com/wired).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>3240</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>353</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>21</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>2866</td>
</tr>
</tbody>
</table>
[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/35181tay/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @wired's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/13lg2287) for full transparency and reproducibility.
At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/13lg2287/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/wired'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
<!--- random size file -->
|
huggingtweets/williamgrobman
|
huggingtweets
| 2021-05-23T04:28:41Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/williamgrobman/1616735910839/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1374605323881779203/c5kjnLQp_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">🔆¯\_(ツ)_/¯❓ 🤖 AI Bot </div>
<div style="font-size: 15px">@williamgrobman bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@williamgrobman's tweets](https://twitter.com/williamgrobman).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3248 |
| Retweets | 51 |
| Short tweets | 223 |
| Tweets kept | 2974 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2wiaiqgc/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @williamgrobman's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/phcsbki0) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/phcsbki0/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/williamgrobman')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/wiifactsplus
|
huggingtweets
| 2021-05-23T04:27:38Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/wiifactsplus/1614218679072/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1336892376963567616/-La5SswS_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Wii Facts Plus 🤖 AI Bot </div>
<div style="font-size: 15px">@wiifactsplus bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@wiifactsplus's tweets](https://twitter.com/wiifactsplus).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 153 |
| Retweets | 5 |
| Short tweets | 0 |
| Tweets kept | 148 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/19wweb3v/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @wiifactsplus's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/28sh6nv9) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/28sh6nv9/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/wiifactsplus')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/whiskyhutch
|
huggingtweets
| 2021-05-23T04:24:26Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/whiskyhutch/1617815806661/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1252749409126772738/POVl38T0_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Sterling 🐝 🤖 AI Bot </div>
<div style="font-size: 15px">@whiskyhutch bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@whiskyhutch's tweets](https://twitter.com/whiskyhutch).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 2893 |
| Retweets | 1516 |
| Short tweets | 345 |
| Tweets kept | 1032 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/24q4cf2m/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @whiskyhutch's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2rv5i0hc) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2rv5i0hc/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/whiskyhutch')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/wherewasmybrain
|
huggingtweets
| 2021-05-23T04:23:23Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/wherewasmybrain/1614466108345/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1278021136387903491/UiDVL30Q_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Titled Goose 🤖 AI Bot </div>
<div style="font-size: 15px">@wherewasmybrain bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@wherewasmybrain's tweets](https://twitter.com/wherewasmybrain).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 2479 |
| Retweets | 528 |
| Short tweets | 235 |
| Tweets kept | 1716 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/23paobou/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @wherewasmybrain's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3jxgjfaw) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3jxgjfaw/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/wherewasmybrain')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/weloc_
|
huggingtweets
| 2021-05-23T04:20:04Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/weloc_/1617167272947/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1320521811675750400/IeM-w2-L_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Weloc 🤖 AI Bot </div>
<div style="font-size: 15px">@weloc_ bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@weloc_'s tweets](https://twitter.com/weloc_).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 1975 |
| Retweets | 53 |
| Short tweets | 350 |
| Tweets kept | 1572 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1mrw3z4v/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @weloc_'s tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/apdvjw3r) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/apdvjw3r/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/weloc_')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/wellypooscene
|
huggingtweets
| 2021-05-23T04:18:56Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/wellypooscene/1616644578299/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/914278196987568128/20uJJCTQ_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">cowtown afficionado 🤖 AI Bot </div>
<div style="font-size: 15px">@wellypooscene bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@wellypooscene's tweets](https://twitter.com/wellypooscene).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 414 |
| Retweets | 40 |
| Short tweets | 35 |
| Tweets kept | 339 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2mtl43mo/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @wellypooscene's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/38ufdelt) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/38ufdelt/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/wellypooscene')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/waynedupreeshow
|
huggingtweets
| 2021-05-23T04:15:34Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/waynedupreeshow/1601333699509/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1292091660323770369/f_RKh7Ra_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">W.E. Dupree 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@waynedupreeshow bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@waynedupreeshow's tweets](https://twitter.com/waynedupreeshow).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>3242</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>204</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>109</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>2929</td>
</tr>
</tbody>
</table>
[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/2rtohy7z/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @waynedupreeshow's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/3rje8xkn) for full transparency and reproducibility.
At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/3rje8xkn/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/waynedupreeshow'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
<!--- random size file -->
|
huggingtweets/wausaubob
|
huggingtweets
| 2021-05-23T04:14:29Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/wausaubob/1616731136628/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1374548471995305986/XVI8-nGF_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Be Like Bob—Stay Home 🤖 AI Bot </div>
<div style="font-size: 15px">@wausaubob bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@wausaubob's tweets](https://twitter.com/wausaubob).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 744 |
| Retweets | 77 |
| Short tweets | 135 |
| Tweets kept | 532 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2h6y30jv/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @wausaubob's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2ocvosw0) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2ocvosw0/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/wausaubob')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/wandererslibrar
|
huggingtweets
| 2021-05-23T04:12:19Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/wandererslibrar/1616799042068/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1160715040632299520/AQWwV1qg_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">The Wanderer's Library 🤖 AI Bot </div>
<div style="font-size: 15px">@wandererslibrar bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@wandererslibrar's tweets](https://twitter.com/wandererslibrar).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 349 |
| Retweets | 87 |
| Short tweets | 20 |
| Tweets kept | 242 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3ukonasm/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @wandererslibrar's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1j01gu1x) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1j01gu1x/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/wandererslibrar')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/wallstreetbets
|
huggingtweets
| 2021-05-23T04:11:10Z | 5 | 2 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/wallstreetbets/1613146226664/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1355305650432188416/zAPHj9_3_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">WallStreetBets 🤖 AI Bot </div>
<div style="font-size: 15px">@wallstreetbets bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@wallstreetbets's tweets](https://twitter.com/wallstreetbets).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3234 |
| Retweets | 298 |
| Short tweets | 294 |
| Tweets kept | 2642 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/hhzrzcsh/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @wallstreetbets's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3gyh32b7) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3gyh32b7/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/wallstreetbets')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/w_mlabateki
|
huggingtweets
| 2021-05-23T04:10:07Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/w_mlabateki/1603890652021/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1234254322092969985/8OT4cl3b_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Wongalethu 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@w_mlabateki bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@w_mlabateki's tweets](https://twitter.com/w_mlabateki).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>3151</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>1149</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>396</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>1606</td>
</tr>
</tbody>
</table>
[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/4oakhwm3/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @w_mlabateki's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/10ag004j) for full transparency and reproducibility.
At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/10ag004j/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/w_mlabateki'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
<!--- random size file -->
|
huggingtweets/vvangone
|
huggingtweets
| 2021-05-23T04:07:38Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/vvangone/1618985675721/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1190256978007904257/TsXH7_nP_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Vincent Van Gone 🤖 AI Bot </div>
<div style="font-size: 15px">@vvangone bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@vvangone's tweets](https://twitter.com/vvangone).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3231 |
| Retweets | 959 |
| Short tweets | 273 |
| Tweets kept | 1999 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/8j4izlsm/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @vvangone's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3bnxlw4j) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3bnxlw4j/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/vvangone')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/vtribbean
|
huggingtweets
| 2021-05-23T04:05:20Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/vtribbean/1620678525750/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1370572034053398529/KTwzI1eg_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">💙 TRIBS 👽 VTuber 💙</div>
<div style="text-align: center; font-size: 14px;">@vtribbean</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from 💙 TRIBS 👽 VTuber 💙.
| Data | 💙 TRIBS 👽 VTuber 💙 |
| --- | --- |
| Tweets downloaded | 3243 |
| Retweets | 578 |
| Short tweets | 531 |
| Tweets kept | 2134 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/223pztng/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @vtribbean's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2hme5b03) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2hme5b03/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/vtribbean')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/voteblake
|
huggingtweets
| 2021-05-23T04:02:54Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/voteblake/1617899664019/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/948045482835681280/O3hp8__2_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">blake box emoji 🤖 AI Bot </div>
<div style="font-size: 15px">@voteblake bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@voteblake's tweets](https://twitter.com/voteblake).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3244 |
| Retweets | 208 |
| Short tweets | 379 |
| Tweets kept | 2657 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/z2oherue/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @voteblake's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/19n7fmfp) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/19n7fmfp/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/voteblake')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/vitalikbuterin
|
huggingtweets
| 2021-05-23T04:01:46Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/vitalikbuterin/1607573059057/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/977496875887558661/L86xyLF4_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">vitalik.eth 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@vitalikbuterin bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@vitalikbuterin's tweets](https://twitter.com/vitalikbuterin).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>3235</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>287</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>122</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>2826</td>
</tr>
</tbody>
</table>
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/12dt6biy/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @vitalikbuterin's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/12ceuzt7) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/12ceuzt7/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/vitalikbuterin'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/viperwave
|
huggingtweets
| 2021-05-23T03:56:06Z | 8 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/viperwave/1617765814112/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1312590774912000000/6E6Ry8aJ_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Travis McElroy "Getting Sexual" Apology Video 🤖 AI Bot </div>
<div style="font-size: 15px">@viperwave bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@viperwave's tweets](https://twitter.com/viperwave).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3211 |
| Retweets | 980 |
| Short tweets | 623 |
| Tweets kept | 1608 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/34nyqo6m/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @viperwave's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/184tfonm) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/184tfonm/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/viperwave')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/vinniehacker
|
huggingtweets
| 2021-05-23T03:53:38Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/vinniehacker/1601347831541/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1280331403415019522/u4yAMDJ1_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Vinnie 😃 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@vinniehacker bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@vinniehacker's tweets](https://twitter.com/vinniehacker).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>442</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>90</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>112</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>240</td>
</tr>
</tbody>
</table>
[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/9fhoiyof/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @vinniehacker's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/1zwwbso6) for full transparency and reproducibility.
At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/1zwwbso6/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/vinniehacker'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
<!--- random size file -->
|
huggingtweets/vikjapan
|
huggingtweets
| 2021-05-23T03:52:28Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/vikjapan/1613790649780/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1348312846954758144/X9G_wGk4_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">びっく@ポジティブに日本を良くしたい🦄 🤖 AI Bot </div>
<div style="font-size: 15px">@vikjapan bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@vikjapan's tweets](https://twitter.com/vikjapan).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 897 |
| Retweets | 14 |
| Short tweets | 464 |
| Tweets kept | 419 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/u2nd957y/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @vikjapan's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/15ytgwxd) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/15ytgwxd/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/vikjapan')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/vfsyes
|
huggingtweets
| 2021-05-23T03:50:08Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/vfsyes/1601526119909/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/965091061923160066/L4aLxCgK_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Victoria Firth-Smith ✌️ 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@vfsyes bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@vfsyes's tweets](https://twitter.com/vfsyes).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>3201</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>791</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>296</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>2114</td>
</tr>
</tbody>
</table>
[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/3zryr6q7/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @vfsyes's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/316yya4e) for full transparency and reproducibility.
At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/316yya4e/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/vfsyes'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
<!--- random size file -->
|
huggingtweets/veryshortstory
|
huggingtweets
| 2021-05-23T03:48:43Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/veryshortstory/1617111091869/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/141070636/42291_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Very Short Story 🤖 AI Bot </div>
<div style="font-size: 15px">@veryshortstory bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@veryshortstory's tweets](https://twitter.com/veryshortstory).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 2223 |
| Retweets | 9 |
| Short tweets | 1 |
| Tweets kept | 2213 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2odcxxfj/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @veryshortstory's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2q00lb2z) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2q00lb2z/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/veryshortstory')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/vercel
|
huggingtweets
| 2021-05-23T03:46:00Z | 4 | 1 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1252531684353998848/6R0-p1Vf_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Vercel 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@vercel bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@vercel's tweets](https://twitter.com/vercel).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>1072</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>339</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>102</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>631</td>
</tr>
</tbody>
</table>
[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/2e8z8gby/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @vercel's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/3svt5mgv) for full transparency and reproducibility.
At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/3svt5mgv/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/vercel'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
<!--- random size file -->
|
huggingtweets/verafiedposter
|
huggingtweets
| 2021-05-23T03:44:52Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/verafiedposter/1616696054193/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1276868958600204289/OgyIJae3_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">big black cloud will come 🤖 AI Bot </div>
<div style="font-size: 15px">@verafiedposter bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@verafiedposter's tweets](https://twitter.com/verafiedposter).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3222 |
| Retweets | 226 |
| Short tweets | 234 |
| Tweets kept | 2762 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2byyqoj9/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @verafiedposter's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/27jpl5l8) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/27jpl5l8/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/verafiedposter')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/vennesports
|
huggingtweets
| 2021-05-23T03:40:48Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/vennesports/1614525364767/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1348717540055285761/b64uTQVw_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">VENN ESPORTS 🤖 AI Bot </div>
<div style="font-size: 15px">@vennesports bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@vennesports's tweets](https://twitter.com/vennesports).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 107 |
| Retweets | 16 |
| Short tweets | 22 |
| Tweets kept | 69 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2wx6lrcs/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @vennesports's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1fch18xq) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1fch18xq/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/vennesports')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/venmosupport
|
huggingtweets
| 2021-05-23T03:38:45Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1330956499644862464/SaEWN6zZ_400x400.png')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Venmo Support 🤖 AI Bot </div>
<div style="font-size: 15px">@venmosupport bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@venmosupport's tweets](https://twitter.com/venmosupport).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3224 |
| Retweets | 0 |
| Short tweets | 3 |
| Tweets kept | 3221 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/28gmfisy/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @venmosupport's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/lmznz3pr) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/lmznz3pr/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/venmosupport')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/venmo
|
huggingtweets
| 2021-05-23T03:37:40Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/venmo/1615340999928/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1330956198456147968/INnnHQyY_400x400.png')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Venmo 🤖 AI Bot </div>
<div style="font-size: 15px">@venmo bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@venmo's tweets](https://twitter.com/venmo).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3227 |
| Retweets | 460 |
| Short tweets | 359 |
| Tweets kept | 2408 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/vi0t04y2/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @venmo's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3rwzfhy7) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3rwzfhy7/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/venmo')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/vecuroniyum
|
huggingtweets
| 2021-05-23T03:35:17Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/vecuroniyum/1618258091681/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1353296744096931841/HGGz6U1F_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">REBOA 🤖 AI Bot </div>
<div style="font-size: 15px">@vecuroniyum bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@vecuroniyum's tweets](https://twitter.com/vecuroniyum).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 312 |
| Retweets | 25 |
| Short tweets | 56 |
| Tweets kept | 231 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3bvb2kz0/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @vecuroniyum's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2l7aj3oi) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2l7aj3oi/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/vecuroniyum')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/vansianmagic
|
huggingtweets
| 2021-05-23T03:33:07Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1304024678738964480/XaiyULdl_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Vanse 🤖 AI Bot </div>
<div style="font-size: 15px">@vansianmagic bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@vansianmagic's tweets](https://twitter.com/vansianmagic).
| Data | Quantity |
| --- | --- |
| Tweets downloaded | 3233 |
| Retweets | 381 |
| Short tweets | 406 |
| Tweets kept | 2446 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1ev1v2vv/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @vansianmagic's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2trfqi5g) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2trfqi5g/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/vansianmagic')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
huggingtweets/vanpelt
|
huggingtweets
| 2021-05-23T03:32:00Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
thumbnail: https://www.huggingtweets.com/vanpelt/1605216961273/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
<style>
@media (prefers-color-scheme: dark) {
.prose { color: #E2E8F0 !important; }
.prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
}
</style>
<section class='prose'>
<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/995187395531161601/4mrM2flB_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Chris Van Pelt (CVP) 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@vanpelt bot</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on [@vanpelt's tweets](https://twitter.com/vanpelt).
<table style='border-width:0'>
<thead style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
<th style='border-width:0'>Data</th>
<th style='border-width:0'>Quantity</th>
</tr>
</thead>
<tbody style='border-width:0'>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Tweets downloaded</td>
<td style='border-width:0'>813</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Retweets</td>
<td style='border-width:0'>87</td>
</tr>
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
<td style='border-width:0'>Short tweets</td>
<td style='border-width:0'>43</td>
</tr>
<tr style='border-width:0'>
<td style='border-width:0'>Tweets kept</td>
<td style='border-width:0'>683</td>
</tr>
</tbody>
</table>
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1oxi9b39/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @vanpelt's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2bfgtsxu) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2bfgtsxu/artifacts) is logged and versioned.
## Intended uses & limitations
### How to use
You can use this model directly with a pipeline for text generation:
<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
model=<span style="color:#FF9800">'huggingtweets/vanpelt'</span>)
generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
### Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
</section>
[](https://twitter.com/intent/follow?screen_name=borisdayma)
<section class='prose'>
For more details, visit the project repository.
</section>
[](https://github.com/borisdayma/huggingtweets)
<!--- random size file -->
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.