modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-08-28 18:27:53
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 525
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-08-28 18:27:52
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
|
stefan-it
| 2023-10-18T12:07:28Z | 6 | 0 |
flair
|
[
"flair",
"pytorch",
"tensorboard",
"token-classification",
"sequence-tagger-model",
"fr",
"base_model:hmteams/teams-base-historic-multilingual-discriminator",
"base_model:finetune:hmteams/teams-base-historic-multilingual-discriminator",
"license:mit",
"region:us"
] |
token-classification
| 2023-10-17T23:31:24Z |
---
language: fr
license: mit
tags:
- flair
- token-classification
- sequence-tagger-model
base_model: hmteams/teams-base-historic-multilingual-discriminator
widget:
- text: Nous recevons le premier numéro d ' un nouveau journal , le Radical - Libéral
, qui paraîtra à Genève deux fois la semaine . Son but est de représenter l '
élément national du radicalisme genevois , en d ' autres termes , de défendre
la politique intransigeante do M . Carteret , en opposition aux tendances du groupe
_ > dont le Genevois est l ' organe . Bétail .
---
# Fine-tuned Flair Model on French HIPE-2020 Dataset (HIPE-2022)
This Flair model was fine-tuned on the
[French HIPE-2020](https://github.com/hipe-eval/HIPE-2022-data/blob/main/documentation/README-hipe2020.md)
NER Dataset using hmTEAMS as backbone LM.
The HIPE-2020 dataset is comprised of newspapers from mid 19C to mid 20C. For information can be found
[here](https://dl.acm.org/doi/abs/10.1007/978-3-030-58219-7_21).
The following NEs were annotated: `loc`, `org`, `pers`, `prod`, `time` and `comp`.
# Results
We performed a hyper-parameter search over the following parameters with 5 different seeds per configuration:
* Batch Sizes: `[8, 4]`
* Learning Rates: `[3e-05, 5e-05]`
And report micro F1-score on development set:
| Configuration | Run 1 | Run 2 | Run 3 | Run 4 | Run 5 | Avg. |
|-----------------|-------------|--------------|--------------|--------------|--------------|--------------|
| bs8-e10-lr3e-05 | [0.8652][1] | [0.8552][2] | [0.8526][3] | [0.8585][4] | [0.8615][5] | 85.86 ± 0.45 |
| bs4-e10-lr3e-05 | [0.8602][6] | [0.8556][7] | [0.8512][8] | [0.8511][9] | [0.8595][10] | 85.55 ± 0.39 |
| bs8-e10-lr5e-05 | [0.85][11] | [0.8592][12] | [0.8534][13] | [0.8473][14] | [0.8505][15] | 85.21 ± 0.41 |
| bs4-e10-lr5e-05 | [0.839][16] | [0.8473][17] | [0.8385][18] | [0.839][19] | [0.8488][20] | 84.25 ± 0.45 |
[1]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[2]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[3]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[4]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[5]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[6]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[7]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[8]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[9]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[10]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[11]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[12]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[13]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[14]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[15]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
[16]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[17]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[18]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[19]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[20]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
The [training log](training.log) and TensorBoard logs (only for hmByT5 and hmTEAMS based models) are also uploaded to the model hub.
More information about fine-tuning can be found [here](https://github.com/stefan-it/hmBench).
# Acknowledgements
We thank [Luisa März](https://github.com/LuisaMaerz), [Katharina Schmid](https://github.com/schmika) and
[Erion Çano](https://github.com/erionc) for their fruitful discussions about Historic Language Models.
Research supported with Cloud TPUs from Google's [TPU Research Cloud](https://sites.research.google/trc/about/) (TRC).
Many Thanks for providing access to the TPUs ❤️
|
stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
|
stefan-it
| 2023-10-18T12:07:12Z | 4 | 0 |
flair
|
[
"flair",
"pytorch",
"tensorboard",
"token-classification",
"sequence-tagger-model",
"fr",
"base_model:hmteams/teams-base-historic-multilingual-discriminator",
"base_model:finetune:hmteams/teams-base-historic-multilingual-discriminator",
"license:mit",
"region:us"
] |
token-classification
| 2023-10-17T20:05:30Z |
---
language: fr
license: mit
tags:
- flair
- token-classification
- sequence-tagger-model
base_model: hmteams/teams-base-historic-multilingual-discriminator
widget:
- text: Nous recevons le premier numéro d ' un nouveau journal , le Radical - Libéral
, qui paraîtra à Genève deux fois la semaine . Son but est de représenter l '
élément national du radicalisme genevois , en d ' autres termes , de défendre
la politique intransigeante do M . Carteret , en opposition aux tendances du groupe
_ > dont le Genevois est l ' organe . Bétail .
---
# Fine-tuned Flair Model on French HIPE-2020 Dataset (HIPE-2022)
This Flair model was fine-tuned on the
[French HIPE-2020](https://github.com/hipe-eval/HIPE-2022-data/blob/main/documentation/README-hipe2020.md)
NER Dataset using hmTEAMS as backbone LM.
The HIPE-2020 dataset is comprised of newspapers from mid 19C to mid 20C. For information can be found
[here](https://dl.acm.org/doi/abs/10.1007/978-3-030-58219-7_21).
The following NEs were annotated: `loc`, `org`, `pers`, `prod`, `time` and `comp`.
# Results
We performed a hyper-parameter search over the following parameters with 5 different seeds per configuration:
* Batch Sizes: `[8, 4]`
* Learning Rates: `[3e-05, 5e-05]`
And report micro F1-score on development set:
| Configuration | Run 1 | Run 2 | Run 3 | Run 4 | Run 5 | Avg. |
|-----------------|-------------|--------------|--------------|--------------|--------------|--------------|
| bs8-e10-lr3e-05 | [0.8652][1] | [0.8552][2] | [0.8526][3] | [0.8585][4] | [0.8615][5] | 85.86 ± 0.45 |
| bs4-e10-lr3e-05 | [0.8602][6] | [0.8556][7] | [0.8512][8] | [0.8511][9] | [0.8595][10] | 85.55 ± 0.39 |
| bs8-e10-lr5e-05 | [0.85][11] | [0.8592][12] | [0.8534][13] | [0.8473][14] | [0.8505][15] | 85.21 ± 0.41 |
| bs4-e10-lr5e-05 | [0.839][16] | [0.8473][17] | [0.8385][18] | [0.839][19] | [0.8488][20] | 84.25 ± 0.45 |
[1]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[2]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[3]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[4]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[5]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[6]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[7]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[8]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[9]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[10]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[11]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[12]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[13]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[14]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[15]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
[16]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[17]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[18]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[19]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[20]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
The [training log](training.log) and TensorBoard logs (only for hmByT5 and hmTEAMS based models) are also uploaded to the model hub.
More information about fine-tuning can be found [here](https://github.com/stefan-it/hmBench).
# Acknowledgements
We thank [Luisa März](https://github.com/LuisaMaerz), [Katharina Schmid](https://github.com/schmika) and
[Erion Çano](https://github.com/erionc) for their fruitful discussions about Historic Language Models.
Research supported with Cloud TPUs from Google's [TPU Research Cloud](https://sites.research.google/trc/about/) (TRC).
Many Thanks for providing access to the TPUs ❤️
|
stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
|
stefan-it
| 2023-10-18T12:07:02Z | 4 | 0 |
flair
|
[
"flair",
"pytorch",
"tensorboard",
"token-classification",
"sequence-tagger-model",
"fr",
"base_model:hmteams/teams-base-historic-multilingual-discriminator",
"base_model:finetune:hmteams/teams-base-historic-multilingual-discriminator",
"license:mit",
"region:us"
] |
token-classification
| 2023-10-17T20:57:16Z |
---
language: fr
license: mit
tags:
- flair
- token-classification
- sequence-tagger-model
base_model: hmteams/teams-base-historic-multilingual-discriminator
widget:
- text: Nous recevons le premier numéro d ' un nouveau journal , le Radical - Libéral
, qui paraîtra à Genève deux fois la semaine . Son but est de représenter l '
élément national du radicalisme genevois , en d ' autres termes , de défendre
la politique intransigeante do M . Carteret , en opposition aux tendances du groupe
_ > dont le Genevois est l ' organe . Bétail .
---
# Fine-tuned Flair Model on French HIPE-2020 Dataset (HIPE-2022)
This Flair model was fine-tuned on the
[French HIPE-2020](https://github.com/hipe-eval/HIPE-2022-data/blob/main/documentation/README-hipe2020.md)
NER Dataset using hmTEAMS as backbone LM.
The HIPE-2020 dataset is comprised of newspapers from mid 19C to mid 20C. For information can be found
[here](https://dl.acm.org/doi/abs/10.1007/978-3-030-58219-7_21).
The following NEs were annotated: `loc`, `org`, `pers`, `prod`, `time` and `comp`.
# Results
We performed a hyper-parameter search over the following parameters with 5 different seeds per configuration:
* Batch Sizes: `[8, 4]`
* Learning Rates: `[3e-05, 5e-05]`
And report micro F1-score on development set:
| Configuration | Run 1 | Run 2 | Run 3 | Run 4 | Run 5 | Avg. |
|-----------------|-------------|--------------|--------------|--------------|--------------|--------------|
| bs8-e10-lr3e-05 | [0.8652][1] | [0.8552][2] | [0.8526][3] | [0.8585][4] | [0.8615][5] | 85.86 ± 0.45 |
| bs4-e10-lr3e-05 | [0.8602][6] | [0.8556][7] | [0.8512][8] | [0.8511][9] | [0.8595][10] | 85.55 ± 0.39 |
| bs8-e10-lr5e-05 | [0.85][11] | [0.8592][12] | [0.8534][13] | [0.8473][14] | [0.8505][15] | 85.21 ± 0.41 |
| bs4-e10-lr5e-05 | [0.839][16] | [0.8473][17] | [0.8385][18] | [0.839][19] | [0.8488][20] | 84.25 ± 0.45 |
[1]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[2]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[3]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[4]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[5]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[6]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[7]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[8]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[9]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[10]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[11]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[12]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[13]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[14]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[15]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
[16]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[17]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[18]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[19]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[20]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
The [training log](training.log) and TensorBoard logs (only for hmByT5 and hmTEAMS based models) are also uploaded to the model hub.
More information about fine-tuning can be found [here](https://github.com/stefan-it/hmBench).
# Acknowledgements
We thank [Luisa März](https://github.com/LuisaMaerz), [Katharina Schmid](https://github.com/schmika) and
[Erion Çano](https://github.com/erionc) for their fruitful discussions about Historic Language Models.
Research supported with Cloud TPUs from Google's [TPU Research Cloud](https://sites.research.google/trc/about/) (TRC).
Many Thanks for providing access to the TPUs ❤️
|
stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
|
stefan-it
| 2023-10-18T12:06:46Z | 7 | 0 |
flair
|
[
"flair",
"pytorch",
"tensorboard",
"token-classification",
"sequence-tagger-model",
"fr",
"base_model:hmteams/teams-base-historic-multilingual-discriminator",
"base_model:finetune:hmteams/teams-base-historic-multilingual-discriminator",
"license:mit",
"region:us"
] |
token-classification
| 2023-10-17T22:28:35Z |
---
language: fr
license: mit
tags:
- flair
- token-classification
- sequence-tagger-model
base_model: hmteams/teams-base-historic-multilingual-discriminator
widget:
- text: Nous recevons le premier numéro d ' un nouveau journal , le Radical - Libéral
, qui paraîtra à Genève deux fois la semaine . Son but est de représenter l '
élément national du radicalisme genevois , en d ' autres termes , de défendre
la politique intransigeante do M . Carteret , en opposition aux tendances du groupe
_ > dont le Genevois est l ' organe . Bétail .
---
# Fine-tuned Flair Model on French HIPE-2020 Dataset (HIPE-2022)
This Flair model was fine-tuned on the
[French HIPE-2020](https://github.com/hipe-eval/HIPE-2022-data/blob/main/documentation/README-hipe2020.md)
NER Dataset using hmTEAMS as backbone LM.
The HIPE-2020 dataset is comprised of newspapers from mid 19C to mid 20C. For information can be found
[here](https://dl.acm.org/doi/abs/10.1007/978-3-030-58219-7_21).
The following NEs were annotated: `loc`, `org`, `pers`, `prod`, `time` and `comp`.
# Results
We performed a hyper-parameter search over the following parameters with 5 different seeds per configuration:
* Batch Sizes: `[8, 4]`
* Learning Rates: `[3e-05, 5e-05]`
And report micro F1-score on development set:
| Configuration | Run 1 | Run 2 | Run 3 | Run 4 | Run 5 | Avg. |
|-----------------|-------------|--------------|--------------|--------------|--------------|--------------|
| bs8-e10-lr3e-05 | [0.8652][1] | [0.8552][2] | [0.8526][3] | [0.8585][4] | [0.8615][5] | 85.86 ± 0.45 |
| bs4-e10-lr3e-05 | [0.8602][6] | [0.8556][7] | [0.8512][8] | [0.8511][9] | [0.8595][10] | 85.55 ± 0.39 |
| bs8-e10-lr5e-05 | [0.85][11] | [0.8592][12] | [0.8534][13] | [0.8473][14] | [0.8505][15] | 85.21 ± 0.41 |
| bs4-e10-lr5e-05 | [0.839][16] | [0.8473][17] | [0.8385][18] | [0.839][19] | [0.8488][20] | 84.25 ± 0.45 |
[1]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[2]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[3]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[4]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[5]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[6]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[7]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[8]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[9]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[10]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[11]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[12]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[13]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[14]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[15]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
[16]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[17]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[18]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[19]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[20]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
The [training log](training.log) and TensorBoard logs (only for hmByT5 and hmTEAMS based models) are also uploaded to the model hub.
More information about fine-tuning can be found [here](https://github.com/stefan-it/hmBench).
# Acknowledgements
We thank [Luisa März](https://github.com/LuisaMaerz), [Katharina Schmid](https://github.com/schmika) and
[Erion Çano](https://github.com/erionc) for their fruitful discussions about Historic Language Models.
Research supported with Cloud TPUs from Google's [TPU Research Cloud](https://sites.research.google/trc/about/) (TRC).
Many Thanks for providing access to the TPUs ❤️
|
stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
|
stefan-it
| 2023-10-18T12:06:41Z | 4 | 0 |
flair
|
[
"flair",
"pytorch",
"tensorboard",
"token-classification",
"sequence-tagger-model",
"fr",
"base_model:hmteams/teams-base-historic-multilingual-discriminator",
"base_model:finetune:hmteams/teams-base-historic-multilingual-discriminator",
"license:mit",
"region:us"
] |
token-classification
| 2023-10-17T20:46:14Z |
---
language: fr
license: mit
tags:
- flair
- token-classification
- sequence-tagger-model
base_model: hmteams/teams-base-historic-multilingual-discriminator
widget:
- text: Nous recevons le premier numéro d ' un nouveau journal , le Radical - Libéral
, qui paraîtra à Genève deux fois la semaine . Son but est de représenter l '
élément national du radicalisme genevois , en d ' autres termes , de défendre
la politique intransigeante do M . Carteret , en opposition aux tendances du groupe
_ > dont le Genevois est l ' organe . Bétail .
---
# Fine-tuned Flair Model on French HIPE-2020 Dataset (HIPE-2022)
This Flair model was fine-tuned on the
[French HIPE-2020](https://github.com/hipe-eval/HIPE-2022-data/blob/main/documentation/README-hipe2020.md)
NER Dataset using hmTEAMS as backbone LM.
The HIPE-2020 dataset is comprised of newspapers from mid 19C to mid 20C. For information can be found
[here](https://dl.acm.org/doi/abs/10.1007/978-3-030-58219-7_21).
The following NEs were annotated: `loc`, `org`, `pers`, `prod`, `time` and `comp`.
# Results
We performed a hyper-parameter search over the following parameters with 5 different seeds per configuration:
* Batch Sizes: `[8, 4]`
* Learning Rates: `[3e-05, 5e-05]`
And report micro F1-score on development set:
| Configuration | Run 1 | Run 2 | Run 3 | Run 4 | Run 5 | Avg. |
|-----------------|-------------|--------------|--------------|--------------|--------------|--------------|
| bs8-e10-lr3e-05 | [0.8652][1] | [0.8552][2] | [0.8526][3] | [0.8585][4] | [0.8615][5] | 85.86 ± 0.45 |
| bs4-e10-lr3e-05 | [0.8602][6] | [0.8556][7] | [0.8512][8] | [0.8511][9] | [0.8595][10] | 85.55 ± 0.39 |
| bs8-e10-lr5e-05 | [0.85][11] | [0.8592][12] | [0.8534][13] | [0.8473][14] | [0.8505][15] | 85.21 ± 0.41 |
| bs4-e10-lr5e-05 | [0.839][16] | [0.8473][17] | [0.8385][18] | [0.839][19] | [0.8488][20] | 84.25 ± 0.45 |
[1]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[2]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[3]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[4]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[5]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[6]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[7]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[8]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[9]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[10]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[11]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[12]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[13]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[14]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[15]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
[16]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[17]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[18]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[19]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[20]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
The [training log](training.log) and TensorBoard logs (only for hmByT5 and hmTEAMS based models) are also uploaded to the model hub.
More information about fine-tuning can be found [here](https://github.com/stefan-it/hmBench).
# Acknowledgements
We thank [Luisa März](https://github.com/LuisaMaerz), [Katharina Schmid](https://github.com/schmika) and
[Erion Çano](https://github.com/erionc) for their fruitful discussions about Historic Language Models.
Research supported with Cloud TPUs from Google's [TPU Research Cloud](https://sites.research.google/trc/about/) (TRC).
Many Thanks for providing access to the TPUs ❤️
|
hmteams/flair-hipe-2022-hipe2020-fr
|
hmteams
| 2023-10-18T12:06:34Z | 6 | 0 |
flair
|
[
"flair",
"pytorch",
"tensorboard",
"token-classification",
"sequence-tagger-model",
"fr",
"base_model:hmteams/teams-base-historic-multilingual-discriminator",
"base_model:finetune:hmteams/teams-base-historic-multilingual-discriminator",
"license:mit",
"region:us"
] |
token-classification
| 2023-10-17T19:54:29Z |
---
language: fr
license: mit
tags:
- flair
- token-classification
- sequence-tagger-model
base_model: hmteams/teams-base-historic-multilingual-discriminator
widget:
- text: Nous recevons le premier numéro d ' un nouveau journal , le Radical - Libéral
, qui paraîtra à Genève deux fois la semaine . Son but est de représenter l '
élément national du radicalisme genevois , en d ' autres termes , de défendre
la politique intransigeante do M . Carteret , en opposition aux tendances du groupe
_ > dont le Genevois est l ' organe . Bétail .
---
# Fine-tuned Flair Model on French HIPE-2020 Dataset (HIPE-2022)
This Flair model was fine-tuned on the
[French HIPE-2020](https://github.com/hipe-eval/HIPE-2022-data/blob/main/documentation/README-hipe2020.md)
NER Dataset using hmTEAMS as backbone LM.
The HIPE-2020 dataset is comprised of newspapers from mid 19C to mid 20C. For information can be found
[here](https://dl.acm.org/doi/abs/10.1007/978-3-030-58219-7_21).
The following NEs were annotated: `loc`, `org`, `pers`, `prod`, `time` and `comp`.
# Results
We performed a hyper-parameter search over the following parameters with 5 different seeds per configuration:
* Batch Sizes: `[8, 4]`
* Learning Rates: `[3e-05, 5e-05]`
And report micro F1-score on development set:
| Configuration | Run 1 | Run 2 | Run 3 | Run 4 | Run 5 | Avg. |
|-----------------|-------------|--------------|--------------|--------------|--------------|--------------|
| bs8-e10-lr3e-05 | [0.8652][1] | [0.8552][2] | [0.8526][3] | [0.8585][4] | [0.8615][5] | 85.86 ± 0.45 |
| bs4-e10-lr3e-05 | [0.8602][6] | [0.8556][7] | [0.8512][8] | [0.8511][9] | [0.8595][10] | 85.55 ± 0.39 |
| bs8-e10-lr5e-05 | [0.85][11] | [0.8592][12] | [0.8534][13] | [0.8473][14] | [0.8505][15] | 85.21 ± 0.41 |
| bs4-e10-lr5e-05 | [0.839][16] | [0.8473][17] | [0.8385][18] | [0.839][19] | [0.8488][20] | 84.25 ± 0.45 |
[1]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[2]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[3]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[4]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[5]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[6]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[7]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[8]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[9]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[10]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[11]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[12]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[13]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[14]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[15]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
[16]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[17]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[18]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[19]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[20]: https://hf.co/stefan-it/hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
The [training log](training.log) and TensorBoard logs (only for hmByT5 and hmTEAMS based models) are also uploaded to the model hub.
More information about fine-tuning can be found [here](https://github.com/stefan-it/hmBench).
# Acknowledgements
We thank [Luisa März](https://github.com/LuisaMaerz), [Katharina Schmid](https://github.com/schmika) and
[Erion Çano](https://github.com/erionc) for their fruitful discussions about Historic Language Models.
Research supported with Cloud TPUs from Google's [TPU Research Cloud](https://sites.research.google/trc/about/) (TRC).
Many Thanks for providing access to the TPUs ❤️
|
ewertonfelipe/taxi-v3-ewerton
|
ewertonfelipe
| 2023-10-18T12:01:42Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-18T12:01:40Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi-v3-ewerton
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.54 +/- 2.73
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="ewertonfelipe/taxi-v3-ewerton", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
jimboHsueh/HW1
|
jimboHsueh
| 2023-10-18T11:48:39Z | 1 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"multiple-choice",
"endpoints_compatible",
"region:us"
] |
multiple-choice
| 2023-10-06T15:39:35Z |
# **Reproduce my result**
**#Environment**
```
pip install -r requirements.txt
```
##**Download**
Download training, validation, testing data, as well as multiple choice model and question answering model.
```
bash ./download.sh
```
##**Multiple Choice**
```
python run_multiple_choice.py \
--context_data <context.json> \
--train_data <train.json> \
--valid_data <valid.json> \
--test_data <test.json> \
--max_seq_length 512 \
--gradient_accumulation_steps 8 \
--model_name_or_path bert-base-chinese \
--learning_rate 2e-5 \
--output_dir <output directory> \
--per_device_train_batch_size 8
```
-**model_name_or_path**: Path to pretrained model.
-**output_dir**: Path to directory which saves the model outputs.
-**context_data**: Path to context.json.
-**train_data**: Path to train.json.
-**valid_data**: Path to valid.json.
-**test_data**: Path to test.json.
##**Question Answering**
```
python run_question_answering.py \
--context_data <context.json> \
--train_data <train.json> \
--valid_data <valid.json> \
--test_data <test.json> \
--max_seq_length 512 \
--gradient_accumulation_steps 8 \
--model_name_or_path hfl/chinese-roberta-wwm-ext-large \
--learning_rate 2e-5 \
--output_dir <output directory> \
--per_device_train_batch_size 8
```
-**model_name_or_path**: Path to pretrained model.
-**output_dir**: Path to directory which saves the model outputs.
-**context_data**: Path to context.json.
-**train_data**: Path to train.json.
-**valid_data**: Path to valid.json.
-**test_data**: Path to test.json.
##**Reproduce my result**
```
bash ./download.sh
bash ./run.sh /path/to/context.json /path/to/test.json /path/to/pred/prediction.csv
```
|
gianlab/swin-tiny-patch4-window7-224-finetuned-plantdisease
|
gianlab
| 2023-10-18T11:47:14Z | 66 | 5 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"swin",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2022-06-24T16:27:59Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-plantdisease
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9689922480620154
---
<!-- 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. -->
# swin-tiny-patch4-window7-224-finetuned-plantdisease
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1032
- Accuracy: 0.9690
## Model description
This model was created by importing the dataset of the photos of diseased plants into Google Colab from kaggle here: https://www.kaggle.com/datasets/emmarex/plantdisease. I then used the image classification tutorial here: https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/image_classification.ipynb
obtaining the following notebook:
https://colab.research.google.com/drive/14ItHnpARBBGaYQCiJwJsnWiiNQnlrIyP?usp=sharing
The possible classified diseases are: Tomato Tomato YellowLeaf Curl Virus , Tomato Late blight ,
Pepper bell Bacterial spot, Tomato Early blight, Potato healthy, Tomato healthy , Tomato Target_Spot , Potato Early blight , Tomato Tomato mosaic virus, Pepper bell healthy, Potato Late blight,
Tomato Septoria leaf spot , Tomato Leaf Mold , Tomato Spider mites Two spotted spider mite , Tomato Bacterial spot .
## Leaf example:
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.1903 | 1.0 | 145 | 0.1032 | 0.9690 |
### Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
|
gianlab/swin-tiny-patch4-window7-224-finetuned-skin-cancer
|
gianlab
| 2023-10-18T11:40:52Z | 105 | 8 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"swin",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:microsoft/swin-tiny-patch4-window7-224",
"base_model:finetune:microsoft/swin-tiny-patch4-window7-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2022-07-02T06:35:54Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
base_model: microsoft/swin-tiny-patch4-window7-224
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-skin-cancer
results:
- task:
type: image-classification
name: Image Classification
dataset:
name: imagefolder
type: imagefolder
args: default
metrics:
- type: accuracy
value: 0.7275449101796407
name: Accuracy
---
<!-- 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. -->
# swin-tiny-patch4-window7-224-finetuned-skin-cancer
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7695
- Accuracy: 0.7275
## Model description
This model was created by importing the dataset of the photos of skin cancer into Google Colab from kaggle here: https://www.kaggle.com/datasets/kmader/skin-cancer-mnist-ham10000 . I then used the image classification tutorial here: https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/image_classification.ipynb
obtaining the following notebook:
https://colab.research.google.com/drive/1bMkXnAvAqjX3J2YJ8wXTNw2Z2pt5KCjy?usp=sharing
The possible classified diseases are: 'Actinic-keratoses', 'Basal-cell-carcinoma', 'Benign-keratosis-like-lesions', 'Dermatofibroma', 'Melanocytic-nevi', 'Melanoma', 'Vascular-lesions' .
## Skin example:
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6911 | 0.99 | 70 | 0.7695 | 0.7275 |
### Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
|
lukekim420/koalpaca-5.8b-finetuned
|
lukekim420
| 2023-10-18T11:39:20Z | 2 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:beomi/KoAlpaca-Polyglot-5.8B",
"base_model:adapter:beomi/KoAlpaca-Polyglot-5.8B",
"region:us"
] | null | 2023-10-18T11:39:14Z |
---
library_name: peft
base_model: beomi/KoAlpaca-Polyglot-5.8B
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
KeiHeityuu/my_awesome_model
|
KeiHeityuu
| 2023-10-18T11:39:12Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"dataset:imdb",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-05-22T09:05:08Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
model-index:
- name: my_awesome_model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.93104
---
<!-- 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. -->
# my_awesome_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2349
- Accuracy: 0.9310
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2301 | 1.0 | 1563 | 0.1888 | 0.9272 |
| 0.1512 | 2.0 | 3126 | 0.2349 | 0.9310 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
jz703/wav2vec2_lj_speech_phonemes_word_level
|
jz703
| 2023-10-18T11:36:48Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:facebook/wav2vec2-large-xlsr-53",
"base_model:finetune:facebook/wav2vec2-large-xlsr-53",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-10-17T02:27:44Z |
---
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2_lj_speech_phonemes_word_level
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# wav2vec2_lj_speech_phonemes_word_level
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3555
- Wer: 0.8317
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---:|
| 8.2048 | 1.53 | 500 | 4.0111 | 1.0 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0
- Datasets 2.14.5
- Tokenizers 0.14.1
|
YuvanKumar/ppo-SnowballTarget
|
YuvanKumar
| 2023-10-18T11:30:42Z | 8 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2023-10-18T08:36:35Z |
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: AgniVardhan/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
gyr66/bert-base-chinese-finetuned-ner
|
gyr66
| 2023-10-18T11:28:13Z | 308 | 8 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"zh",
"dataset:gyr66/privacy_detection",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-18T08:48:01Z |
---
language:
- zh
tags:
- generated_from_trainer
datasets:
- gyr66/privacy_detection
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-chinese-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: gyr66/privacy_detection
type: gyr66/privacy_detection
config: privacy_detection
split: train
args: privacy_detection
metrics:
- name: Precision
type: precision
value: 0.65322
- name: Recall
type: recall
value: 0.74169
- name: F1
type: f1
value: 0.69465
- name: Accuracy
type: accuracy
value: 0.90517
---
<!-- 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. -->
# bert-base-chinese-finetuned-ner
This model is a fine-tuned version of [Danielwei0214/bert-base-chinese-finetuned-ner](https://huggingface.co/Danielwei0214/bert-base-chinese-finetuned-ner) on the [gyr66/privacy_detection](https://huggingface.co/datasets/gyr66/privacy_detection) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7929
- Precision: 0.6532
- Recall: 0.7417
- F1: 0.6947
- Accuracy: 0.9052
## Model description
The model is used for competition: "https://www.datafountain.cn/competitions/472"
## Training and evaluation data
The training and evaluation data is from [gyr66/privacy_detection](https://huggingface.co/datasets/gyr66/privacy_detection) dataset.
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 56
- eval_batch_size: 56
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
### Framework versions
- Transformers 4.27.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.2
|
dru-ac/ArGTC
|
dru-ac
| 2023-10-18T11:24:25Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bloom",
"text-classification",
"dataset:dru-ac/ArTopicDS",
"dataset:dru-ac/ArTopicDS-Books",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-17T09:55:42Z |
---
datasets:
- dru-ac/ArTopicDS
- dru-ac/ArTopicDS-Books
metrics:
- accuracy
- precision
- recall
pipeline_tag: text-classification
---
`ArGTClass` is a `bloomz` based classification model, finetuned to categorize a comprehensive spectrum
of fourteen distinct subjects that are Religion,
Finance and Economics, Politics, Medical, Cul-
ture, Sports, Science and Technology, Anthro-
pology and Sociology, Art and Literature, Edu-
cation, History, Language and Linguistics, Law,
as well as Philosophy in Arabic.
For more details, check out our [paper](here)
Finetuning code in the following notebook: [](https://colab.research.google.com/drive/106oPnGhe8B_BCgV6LnJbvVZNv4mCu9Zv?usp=sharing)
### Full classification example (CPU)
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("dru-ac/ArGTClass")
model = AutoModelForSequenceClassification.from_pretrained("dru-ac/ArGTClass")
text = " .قصفت إسرائيل مستشفى المعمداني في مدينة غزة، والذي خلف مئات الشهداء والجرحى"
inputs = tokenizer(text, return_tensors= 'pt')
outputs = model(**inputs)
ind = outputs.logits.argmax(dim=-1)[0]
predicted_class = model.config.id2label[ind.item()]
```
### Full classification example (GPU)
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("dru-ac/ArGTClass")
model = AutoModelForSequenceClassification.from_pretrained("dru-ac/ArGTClass", device_map = 'auto')
text = " .قصفت إسرائيل مستشفى المعمداني في مدينة غزة، والذي خلف مئات الشهداء والجرحى"
inputs = tokenizer(text, return_tensors= 'pt').to("cuda")
outputs = model(**inputs)
ind = outputs.logits.argmax(dim=-1)[0]
predicted_class = model.config.id2label[ind.item()]
```
### Pipeline example (CPU & GPU)
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("dru-ac/ArGTClass")
model = AutoModelForSequenceClassification.from_pretrained("dru-ac/ArGTClass", device_map = 'auto')
classifier = pipeline("text-classification", model=model, tokenizer= tokenizer)
text = " .قصفت إسرائيل مستشفى المعمداني في مدينة غزة، والذي خلف مئات الشهداء والجرحى"
classifier(text)
```
|
Against61/mistral-finetuned-samsum
|
Against61
| 2023-10-18T11:18:22Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
"base_model:finetune:TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
"license:apache-2.0",
"region:us"
] | null | 2023-10-12T05:51:24Z |
---
license: apache-2.0
base_model: TheBloke/Mistral-7B-Instruct-v0.1-GPTQ
tags:
- generated_from_trainer
model-index:
- name: mistral-finetuned-samsum
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mistral-finetuned-samsum
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Rajkumar7093626243/my-pet-dog
|
Rajkumar7093626243
| 2023-10-18T11:13:07Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-18T11:08:53Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### My-Pet-Dog Dreambooth model trained by Rajkumar7093626243 following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: GoX19932gAS
Sample pictures of this concept:
.jpg)
.jpg)
|
chrlie/ppo-LunarLander-v2
|
chrlie
| 2023-10-18T11:12:24Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-18T11:09:55Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 256.76 +/- 18.79
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
bleugreen/mistral_summary
|
bleugreen
| 2023-10-18T11:10:25Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-10T02:57:06Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
Siri12/my-pet-dog
|
Siri12
| 2023-10-18T11:09:59Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-18T11:05:56Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### My-Pet-Dog Dreambooth model trained by Siri12 following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: GoX19932gAS
Sample pictures of this concept:
.jpg)
|
TheBloke/rpguild-chatml-13B-GPTQ
|
TheBloke
| 2023-10-18T10:53:49Z | 19 | 4 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"roleplay",
"en",
"dataset:chargoddard/rpguild",
"base_model:chargoddard/rpguild-chatml-13b",
"base_model:quantized:chargoddard/rpguild-chatml-13b",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-10-18T10:20:12Z |
---
base_model: chargoddard/rpguild-chatml-13b
datasets:
- chargoddard/rpguild
inference: false
language:
- en
license: cc-by-nc-4.0
model_creator: Charles Goddard
model_name: RPGuild ChatML 13B
model_type: llama
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
quantized_by: TheBloke
tags:
- llama
- roleplay
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# RPGuild ChatML 13B - GPTQ
- Model creator: [Charles Goddard](https://huggingface.co/chargoddard)
- Original model: [RPGuild ChatML 13B](https://huggingface.co/chargoddard/rpguild-chatml-13b)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Charles Goddard's RPGuild ChatML 13B](https://huggingface.co/chargoddard/rpguild-chatml-13b).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/rpguild-chatml-13B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/rpguild-chatml-13B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/rpguild-chatml-13B-GGUF)
* [Charles Goddard's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/chargoddard/rpguild-chatml-13b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `cc-by-nc-4.0`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Charles Goddard's RPGuild ChatML 13B](https://huggingface.co/chargoddard/rpguild-chatml-13b).
<!-- licensing end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/rpguild-chatml-13B-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/rpguild-chatml-13B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/rpguild-chatml-13B-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/rpguild-chatml-13B-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/rpguild-chatml-13B-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 14.55 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/rpguild-chatml-13B-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/rpguild-chatml-13B-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/rpguild-chatml-13B-GPTQ:gptq-4bit-32g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `rpguild-chatml-13B-GPTQ`:
```shell
mkdir rpguild-chatml-13B-GPTQ
huggingface-cli download TheBloke/rpguild-chatml-13B-GPTQ --local-dir rpguild-chatml-13B-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir rpguild-chatml-13B-GPTQ
huggingface-cli download TheBloke/rpguild-chatml-13B-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir rpguild-chatml-13B-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir rpguild-chatml-13B-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/rpguild-chatml-13B-GPTQ --local-dir rpguild-chatml-13B-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/rpguild-chatml-13B-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/rpguild-chatml-13B-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/rpguild-chatml-13B-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `rpguild-chatml-13B-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
- Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/rpguild-chatml-13B-GPTQ --port 3000 --quantize gptq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers optimum
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/rpguild-chatml-13B-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility.
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Charles Goddard's RPGuild ChatML 13B
It's a roleplay model! Trained on ~50k examples of human written roleplay sessions. Not a hint of gpt-flavor writing. Very creative and very able to roll with the punches.
Does tend to speak for you more than it should and has a very, very strong bias towards speech in quotes.
Uses ChatML prompt format, with optional length suffixes:
```
<|im_start|>system
Enter roleplay mode. You are Steve.
Steve is a nasty little man and solves all his problems by punching people in the face.<|im_end|>
<|im_start|>Gundalf, Gandalf's cousin with a gun
Gundalf runs frantically up to Steve and begins yelling. "We have a big problem, Steve!"<|im_end|>
<|im_start|>Steve (Length: short)
"What is it now Gundalf? Do you want me to punch you in the face?" Steve asked, looking down at him. He was pretty sure that this guy wasn't worth the trouble of punching him in the face, but he didn't like to leave loose ends hanging either.
"There's been an incident," Gundalf said quickly, "A dwarf has stolen some gold from Smaug."
"Well I don't care about any of those things," Steve responded, turning away. <|im_end|>
```
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
guardianbotanicalsbloodbalancereview/guardianbotanicalsbloodbalancereview
|
guardianbotanicalsbloodbalancereview
| 2023-10-18T10:53:39Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-10-18T10:52:28Z |
---
license: openrail
language:
- en
library_name: asteroid
tags:
Guardian Botanicals Blood Balance
[Guardian Botanicals Blood Balance](https://atozsupplement.com/guardian-botanicals-blood-balance/) take into consideration, person desires and desires might also additionally moreover range, so it is crucial to paintings cautiously together with your healthcare organisation to increase a personalized graph for handling and controlling your blood sugar degrees.
Click Here For More Details:- https://atozsupplement.com/guardian-botanicals-blood-balance/
|
maywell/Synatra_TbST02M_IN01
|
maywell
| 2023-10-18T10:43:21Z | 2,246 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"ko",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-16T09:09:13Z |
---
language:
- ko
library_name: transformers
pipeline_tag: text-generation
license: cc-by-nc-4.0
---
# **Synatra_TbST02M_IN01**
Made by StableFluffy
**Contact (Do not Contact for personal things.)**
Discord : is.maywell
Telegram : AlzarTakkarsen
## License
This model is strictly [*non-commercial*](https://creativecommons.org/licenses/by-nc/4.0/) (**cc-by-nc-4.0**) use only which takes priority over the **MISTRAL APACHE 2.0**.
The "Model" is completely free (ie. base model, derivates, merges/mixes) to use for non-commercial purposes as long as the the included **cc-by-nc-4.0** license in any parent repository, and the non-commercial use statute remains, regardless of other models' licences.
The licence can be changed after new model released. If you are to use this model for commercial purpose, Contact me.
## Model Details
**Base Model**
[mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
**Trained On**
A100 80GB * 4
# **Model Benchmark**
X
```
> Readme format: [beomi/llama-2-ko-7b](https://huggingface.co/beomi/llama-2-ko-7b)
---
|
hung200504/bert-9
|
hung200504
| 2023-10-18T10:31:32Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"question-answering",
"generated_from_trainer",
"base_model:deepset/bert-base-cased-squad2",
"base_model:finetune:deepset/bert-base-cased-squad2",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-18T10:31:09Z |
---
license: cc-by-4.0
base_model: deepset/bert-base-cased-squad2
tags:
- generated_from_trainer
model-index:
- name: bert-9
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-9
This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-07
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Praga-6000/rl_course_vizdoom_health_gathering_supreme
|
Praga-6000
| 2023-10-18T10:30:17Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-18T10:30:11Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 10.12 +/- 5.08
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r Praga-6000/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
hung200504/bert-8
|
hung200504
| 2023-10-18T10:19:02Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"question-answering",
"generated_from_trainer",
"base_model:deepset/bert-base-cased-squad2",
"base_model:finetune:deepset/bert-base-cased-squad2",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-18T10:11:53Z |
---
license: cc-by-4.0
base_model: deepset/bert-base-cased-squad2
tags:
- generated_from_trainer
model-index:
- name: bert-8
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-8
This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Eldorico/Angela_Aspirant
|
Eldorico
| 2023-10-18T10:15:34Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-10-18T09:59:33Z |
---
license: creativeml-openrail-m
---
|
amanpelago/pelago-sentence-transformer-v2
|
amanpelago
| 2023-10-18T09:44:59Z | 1 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-10-18T09:44:53Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# amanpelago/pelago-sentence-transformer-v2
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('amanpelago/pelago-sentence-transformer-v2')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=amanpelago/pelago-sentence-transformer-v2)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 11780 with parameters:
```
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.TripletLoss.TripletLoss` with parameters:
```
{'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 5}
```
Parameters of the fit()-Method:
```
{
"epochs": 5,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 100,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
hung200504/bert-7
|
hung200504
| 2023-10-18T09:43:08Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"question-answering",
"generated_from_trainer",
"base_model:deepset/bert-base-cased-squad2",
"base_model:finetune:deepset/bert-base-cased-squad2",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-18T09:42:54Z |
---
license: cc-by-4.0
base_model: deepset/bert-base-cased-squad2
tags:
- generated_from_trainer
model-index:
- name: bert-7
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-7
This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
SHENMU007/neunit_BASE_V9.5.16
|
SHENMU007
| 2023-10-18T09:41:40Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"speecht5",
"text-to-audio",
"1.1.0",
"generated_from_trainer",
"zh",
"dataset:facebook/voxpopuli",
"base_model:microsoft/speecht5_tts",
"base_model:finetune:microsoft/speecht5_tts",
"license:mit",
"endpoints_compatible",
"region:us"
] |
text-to-audio
| 2023-10-13T03:50:30Z |
---
language:
- zh
license: mit
base_model: microsoft/speecht5_tts
tags:
- 1.1.0
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: SpeechT5 TTS Dutch neunit
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# SpeechT5 TTS Dutch neunit
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
### Training results
### Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
phlobo/xmen-en-ce-medmentions
|
phlobo
| 2023-10-18T09:36:33Z | 6 | 0 |
xmen
|
[
"xmen",
"pytorch",
"bert",
"medical",
"arxiv:2310.11275",
"region:us"
] | null | 2023-10-18T09:31:56Z |
---
library_name: xmen
tags:
- medical
---
xMEN cross-encoder model trained on MedMentions.
For details, see: https://github.com/hpi-dhc/xmen and https://arxiv.org/abs/2310.11275
|
phlobo/xmen-de-ce-medmentions
|
phlobo
| 2023-10-18T09:33:00Z | 4 | 0 |
xmen
|
[
"xmen",
"pytorch",
"roberta",
"medical",
"arxiv:2310.11275",
"region:us"
] | null | 2023-10-18T08:44:56Z |
---
library_name: xmen
tags:
- medical
---
xMEN cross-encoder model trained on machine-translated version of MedMentions.
For details, see: https://github.com/hpi-dhc/xmen and https://arxiv.org/abs/2310.11275
|
Erica-CHAI/erica-class-butterflies-32
|
Erica-CHAI
| 2023-10-18T09:29:54Z | 1 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"pytorch",
"unconditional-image-generation",
"diffusion-models-class",
"license:mit",
"diffusers:DDPMPipeline",
"region:us"
] |
unconditional-image-generation
| 2023-10-18T09:29:09Z |
---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of cute 🦋.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('Erica-CHAI/erica-class-butterflies-32')
image = pipeline().images[0]
image
```
|
cold11w/sd-class-butterflies-32
|
cold11w
| 2023-10-18T09:11:04Z | 1 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"pytorch",
"unconditional-image-generation",
"diffusion-models-class",
"license:mit",
"diffusers:DDPMPipeline",
"region:us"
] |
unconditional-image-generation
| 2023-10-18T09:10:38Z |
---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of cute 🦋.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('cold11w/sd-class-butterflies-32')
image = pipeline().images[0]
image
```
|
kakafei/aaa
|
kakafei
| 2023-10-18T09:10:48Z | 0 | 0 | null |
[
"arxiv:1910.09700",
"license:apache-2.0",
"region:us"
] | null | 2023-10-18T08:48:03Z |
---
license: apache-2.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
koankoan/Shimura_Tatsumi_XLModel
|
koankoan
| 2023-10-18T09:06:29Z | 2 | 0 |
diffusers
|
[
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"dataset:koankoan/ShimuraTatsumi",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-10-18T08:16:14Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: Shimura Tatsumi Style
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: false
datasets:
- koankoan/ShimuraTatsumi
---
# LoRA DreamBooth - koankoan/Shimura_Tatsumi_XLModel
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0 trained on @fffiloni's SD-XL trainer.
The weights were trained on the concept prompt:
```
Shimura Tatsumi Style
```
Use this keyword to trigger your custom model in your prompts.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Usage
Make sure to upgrade diffusers to >= 0.19.0:
```
pip install diffusers --upgrade
```
In addition make sure to install transformers, safetensors, accelerate as well as the invisible watermark:
```
pip install invisible_watermark transformers accelerate safetensors
```
To just use the base model, you can run:
```python
import torch
from diffusers import DiffusionPipeline, AutoencoderKL
device = "cuda" if torch.cuda.is_available() else "cpu"
vae = AutoencoderKL.from_pretrained('madebyollin/sdxl-vae-fp16-fix', torch_dtype=torch.float16)
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
vae=vae, torch_dtype=torch.float16, variant="fp16",
use_safetensors=True
)
pipe.to(device)
# This is where you load your trained weights
specific_safetensors = "pytorch_lora_weights.safetensors"
lora_scale = 0.9
pipe.load_lora_weights(
'koankoan/Shimura_Tatsumi_XLModel',
weight_name = specific_safetensors,
# use_auth_token = True
)
prompt = "A majestic Shimura Tatsumi Style jumping from a big stone at night"
image = pipe(
prompt=prompt,
num_inference_steps=50,
cross_attention_kwargs={"scale": lora_scale}
).images[0]
```
|
kowalsky/SpaceInvaders-v4
|
kowalsky
| 2023-10-18T09:06:10Z | 4 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-18T09:05:38Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 490.00 +/- 137.33
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga kowalsky -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga kowalsky -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga kowalsky
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 500000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
yfyeung/icefall-asr-gigaspeech-zipformer-2023-10-17
|
yfyeung
| 2023-10-18T09:02:02Z | 0 | 2 | null |
[
"tensorboard",
"onnx",
"license:apache-2.0",
"region:us"
] | null | 2023-10-17T09:17:30Z |
---
license: apache-2.0
---
This repo contains pre-trained models, checkpoints, training logs and decoding results of the following pull-request:
https://github.com/k2-fsa/icefall/pull/1254
|
RogerB/afro-xlmr-large-kinte-domain-kinte-task-kin-sent1
|
RogerB
| 2023-10-18T08:59:19Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"text-classification",
"generated_from_trainer",
"base_model:RogerB/afro-xlmr-large-kin-tweets-pretrained",
"base_model:finetune:RogerB/afro-xlmr-large-kin-tweets-pretrained",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-11T10:16:34Z |
---
license: mit
base_model: RogerB/afro-xlmr-large-kinte-domain-kinte-task
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: afro-xlmr-large-kinte-domain-kinte-task-kin-sent1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# afro-xlmr-large-kinte-domain-kinte-task-kin-sent1
This model is a fine-tuned version of [RogerB/afro-xlmr-large-kinte-domain-kinte-task](https://huggingface.co/RogerB/afro-xlmr-large-kinte-domain-kinte-task) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9477
- F1: 0.7086
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 606386
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.9114 | 1.0 | 1013 | 0.6714 | 0.7147 |
| 0.7347 | 2.0 | 2026 | 0.5420 | 0.7965 |
| 0.6399 | 3.0 | 3039 | 0.5070 | 0.8269 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
hankokk/q-FrozenLake-v1-4x4-noSlippery
|
hankokk
| 2023-10-18T08:44:54Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-18T05:44:43Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="hankokk/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
Changlil/cloth-dreambooth
|
Changlil
| 2023-10-18T08:44:17Z | 0 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-18T08:31:38Z |
---
license: creativeml-openrail-m
base_model: tailor-sd15-512x640-110k
instance_prompt: a photo of sks jacket
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - Changlil/cloth-dreambooth
This is a dreambooth model derived from tailor-sd15-512x640-110k. The weights were trained on a photo of sks jacket using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
joseluhf11/symptom_encoder_v9
|
joseluhf11
| 2023-10-18T08:42:47Z | 13 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-10-18T08:42:16Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 128 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 984 with parameters:
```
{'batch_size': 128}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 50,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 4920,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 128, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF
|
TheBloke
| 2023-10-18T08:40:29Z | 206 | 8 |
transformers
|
[
"transformers",
"gguf",
"mistral",
"en",
"dataset:PocketDoc/Floyd-Text-Adventures",
"dataset:PocketDoc/Choose-Your-Story-Long-Text-Adventures",
"base_model:PocketDoc/Dans-AdventurousWinds-Mk2-7b",
"base_model:quantized:PocketDoc/Dans-AdventurousWinds-Mk2-7b",
"license:apache-2.0",
"region:us"
] | null | 2023-10-18T08:34:10Z |
---
base_model: PocketDoc/Dans-AdventurousWinds-Mk2-7b
datasets:
- PocketDoc/Floyd-Text-Adventures
- PocketDoc/Choose-Your-Story-Long-Text-Adventures
inference: false
language:
- en
license: apache-2.0
model_creator: PocketDoc Labs
model_name: Dans AdventurousWinds Mk2 7B
model_type: mistral
prompt_template: '[Genres: Science Fiction]
[Tags: humor, old school, sci fi]
[Mode: Adventure]
[Description: A puzzle about committing acts of financial skulduggery and exploiting
ridiculous magical items.]
[Misc: Writing era: 1993]
[Intro]
It is the year 2045. You are a young man in his twenties living in New York City.
Your father was an inventor who died when you were very small; your mother raised
you alone for many years until she remarried. Now you live with your stepfather,
but he doesn''t care much for you and has never given you any money to help support
yourself. You have no job and little hope of getting one because of your lack of
experience. However, you do have some unusual abilities that could be put to good
use if only you knew how...
> {prompt}
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Dans AdventurousWinds Mk2 7B - GGUF
- Model creator: [PocketDoc Labs](https://huggingface.co/PocketDoc)
- Original model: [Dans AdventurousWinds Mk2 7B](https://huggingface.co/PocketDoc/Dans-AdventurousWinds-Mk2-7b)
<!-- description start -->
## Description
This repo contains GGUF format model files for [PocketDoc Labs's Dans AdventurousWinds Mk2 7B](https://huggingface.co/PocketDoc/Dans-AdventurousWinds-Mk2-7b).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF)
* [PocketDoc Labs's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/PocketDoc/Dans-AdventurousWinds-Mk2-7b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Adventure
```
[Genres: Science Fiction]
[Tags: humor, old school, sci fi]
[Mode: Adventure]
[Description: A puzzle about committing acts of financial skulduggery and exploiting ridiculous magical items.]
[Misc: Writing era: 1993]
[Intro]
It is the year 2045. You are a young man in his twenties living in New York City. Your father was an inventor who died when you were very small; your mother raised you alone for many years until she remarried. Now you live with your stepfather, but he doesn't care much for you and has never given you any money to help support yourself. You have no job and little hope of getting one because of your lack of experience. However, you do have some unusual abilities that could be put to good use if only you knew how...
> {prompt}
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [dans-adventurouswinds-mk2-7b.Q2_K.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [dans-adventurouswinds-mk2-7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [dans-adventurouswinds-mk2-7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [dans-adventurouswinds-mk2-7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [dans-adventurouswinds-mk2-7b.Q4_0.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [dans-adventurouswinds-mk2-7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [dans-adventurouswinds-mk2-7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [dans-adventurouswinds-mk2-7b.Q5_0.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [dans-adventurouswinds-mk2-7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [dans-adventurouswinds-mk2-7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [dans-adventurouswinds-mk2-7b.Q6_K.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [dans-adventurouswinds-mk2-7b.Q8_0.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF and below it, a specific filename to download, such as: dans-adventurouswinds-mk2-7b.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF dans-adventurouswinds-mk2-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF dans-adventurouswinds-mk2-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m dans-adventurouswinds-mk2-7b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[Genres: Science Fiction]\n[Tags: humor, old school, sci fi]\n[Mode: Adventure]\n[Description: A puzzle about committing acts of financial skulduggery and exploiting ridiculous magical items.]\n[Misc: Writing era: 1993]\n[Intro]\nIt is the year 2045. You are a young man in his twenties living in New York City. Your father was an inventor who died when you were very small; your mother raised you alone for many years until she remarried. Now you live with your stepfather, but he doesn't care much for you and has never given you any money to help support yourself. You have no job and little hope of getting one because of your lack of experience. However, you do have some unusual abilities that could be put to good use if only you knew how...\n\n> {prompt}"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF", model_file="dans-adventurouswinds-mk2-7b.Q4_K_M.gguf", model_type="mistral", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: PocketDoc Labs's Dans AdventurousWinds Mk2 7B
**16k training sequences**
# What is the model for?
This model is proficient in crafting text-based adventure games. It can both concise replies and more expansive, novel-like descriptions. The ability to alternate between these two response styles can be triggered by a distinct system message.
# What's in the sausage?
This model was trained on [Mistral-7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) using a custom version of the floyd and cys datasets from the skein text adventure dataset. The dataset has been improved over what was used in my previous model Dans-AdventurousWinds, in addition it had been trained on 16k sequence lengths.
## Prompt format and examples:
#### Format description:
Traditional adventure format with a description of the genre, tags, and other misc information at the top followed by an optional introductory message. User messages are prefixed with two new lines and "> ", model messages are one new line after the last user message or the description message if an introductory message is desired.
#### Examples of shorter responses:
> [Genres: Science Fiction]
> [Tags: humor, old school, sci fi]
> [Mode: Adventure]
> [Description: A puzzle about committing acts of financial skulduggery and exploiting ridiculous magical items.]
> [Misc: Writing era: 1993]
> [Intro]
> You are an interstellar trader.
>
> On your way to the galactic capital of Coruscant to sell a large quantity of fettucini, you make a detour through a planetary system with a reputation for being dangerous and unstable. The reason is simple -- there is a very powerful magical item known as "The Sword Of Damocles" up for sale. You have no idea what it does, but you've heard that the previous owners all ended up dead or broke. In other words, these people were so desperate to get rid of the sword that they would probably be willing to take almost any price. It sounds like a great deal!
>
> Of course, you don't have enough money to buy the sword outright, which means that you will need to find some way to finance the purchase. There is only one possible source of funds in this part of space -- the loan sharks who operate out of a nearby planet called Riggerton. But these loans come at a high interest rate; if you can't pay them back quickly, you may end up losing everything.
>
> You also know that there are several potential buyers vying for ownership of the sword, including some of the most ruthless criminals in the galaxy. These people might be willing to kill each other over this object, making it more valuable than ever before! However, they are notoriously paranoid and suspicious, so you must proceed with extreme caution when dealing with them...
>
> Finally, there is always the chance that someone else will beat you to the punch by buying the sword first. If that happens then you won't be able to afford it anymore anyway, so maybe it doesn't matter too much?
>
> In any case, good luck! And remember: never borrow money from anyone unless you absolutely trust him completely. Otherwise he could turn around and sell YOU into slavery instead!
>
> Ready? Then let's begin...
>
> \> You snap out of your daydream and remember you're still in port.
> You should probably get ready to go somewhere now...
>
> There are three main places where traders usually hang out: the docking bay (where ships land), the casino (a place where people gamble) and the black market (an illegal bazaar). Each has its own advantages and disadvantages depending on what kind of goods you want to trade. For example, the docking bay is the safest option because it's run by the government, but it charges higher taxes; while the black market is riskier but cheaper.
>
> So where do you think you ought to go?
>
> \> You get ready for launch
> Okay, I guess we better start looking for something interesting then...
>
> Before we leave though, I just wanted to mention that there are two ways to travel between planets: hyperspace jumps and wormholes. Both methods require special technology that only exists inside starships, but they work differently.
>
> A hyperspace jump involves using a hyperdrive engine to accelerate faster than light speed until you reach another galaxy entirely. Once there, you slow down again and return home. This method takes longer than a wormhole, but it allows you to visit distant worlds without having to worry about getting lost along the way.
>
> Wormholes however, allow you to travel instantly across vast distances without needing to slow down at either end. Unfortunately, this type of transportation isn't available everywhere, plus it requires extremely powerful computers to map out their locations accurately. Still, if you happen to find yourself near one of these things then I strongly recommend taking advantage of it since it saves time.
>
> Anyway, let me know whenever you're ready to go. We'll see how far away our next stop lies...
>
> \> You check the database on wormhole technology
> Okay, here goes nothing...
>
> According to my research, there are currently three types of wormholes known to science: stable, unstable and artificial. Stable ones occur naturally throughout the universe and tend to stay open permanently. Unstable ones close after passing through once, whereas artificially created ones remain open indefinitely.
>
> As far as I know, none of these types are suitable for commercial use yet. However, scientists believe that further development will eventually lead to practical applications in areas such as teleportation and faster-than-light travel. Until then though, I doubt whether anything useful can be achieved simply by reading books about the subject.
>
> Sorry if I disappointed you there, but I hope this information proves useful nonetheless. Good luck with whatever comes next!
>
> P.S.: Before leaving, please ensure that all loose objects have been put away properly. Otherwise they could fall off the ship during flight and cause damage later on. Thanks!
#### Examples of longer novel like responses:
> [Genres: grimdark fantasy] [Tags: Fantasy, Grimdark, Serious, Villain Protagonist, War] [Description: This story is definitely more "story" than "game", however there are two distinct paths that can be followed, each with their own pitfalls and additional choices. This story can get long, and assuming you're surviving, years do pass in it and you and your environment will change.] [First message intro] [Mode: Interactive Storyteller]
> You have been a mercenary for many years now. You are an accomplished warrior and battlefield commander. Your company consists of about 50 men and women. Most are veteran soldiers from different countries, some even from as far away as the Americas. They are all loyal to you. The only thing keeping them from being devoted followers would be your atheism.
>
> The war has raged on for many years now. The enemy, the Kingdom of Erenland, is a nation of fanatics who worship a single god called Galdrin. Their religion spread across the land like wildfire after their king ascended to the throne. He declared himself a prophet and made his people believe they were invincible. They started invading neighboring nations to bring them into the fold. The king of your homeland, King Dagor, was one of the first to resist this. When he refused to allow missionaries into his country, the Erenlanders invaded anyway. It took several years before King Dagor managed to gather enough forces to repel the invasion. The war lasted for decades and finally ended when Dagor's grandson ascended to the throne. At that point, both sides realized how much blood had already been spilled and agreed to a truce.
>
> Unfortunately, the peace didn't last very long. A few years ago, King Dagor II died without any children. His cousin became the new monarch but she was weak and incompetent. She allowed her advisors to make most of the important decisions while she spent her time partying with nobles from other nations. One of these advisors convinced the queen to send troops to help quell rebellions that were taking place in the Erenlander cities. These rebellions were caused by dissatisfaction with the way the crown was handling things. They wanted to overthrow their ruler and install a new one that would listen to them.
>
> When word reached the court that the rebels had succeeded in killing the king, everyone panicked. The Queen ordered her army to march north immediately. Unfortunately, she hadn't thought through what would happen if the enemy army attacked during this period of chaos. The result was disastrous. The Erenlanders caught our army completely off guard and annihilated us almost entirely. Only a handful survived to tell the tale. Among those survivors was you.
>
> You have come back home to bury your fallen comrades. You know you won't find rest until you avenge their deaths. But where do you begin? How do you stop an entire nation from going to war against yours? And how do you convince others to join you when they see you as nothing more than a madman bent on destruction?
>
> These questions haunt you every night. You lie awake staring at the ceiling wondering how you could possibly make things right again. Then you remember something...
>
> There was once a great hero named Galadar who lived hundreds of years ago. He fought against tyranny and oppression throughout his lifetime. People said that he possessed magical powers which gave him strength beyond anything mortal. Some even claimed that he walked among the stars. After retiring from active duty, Galadar vanished mysteriously. No one knows where he went or why. Rumors say that he returned to fight alongside the gods against evil forces threatening to destroy existence itself. Whatever happened to him, no one knows for sure. All we do know is that his legacy lives on today through those who follow his example. Perhaps you too can become such a person. Perhaps you can use your talents to save the world from darkness just like he did so long ago. If you feel ready, then take up arms and prepare yourself for battle!
>
> Your journey begins here...
>
> You wake up feeling refreshed after a good night's sleep. You look around your bedroom and notice that everything seems normal. There isn't anyone else around except for your wife, who lies sleeping next to you. You turn towards her and smile softly. She stirs slightly and mumbles something incoherent. You stroke her hair gently and whisper sweet nothings into her ear. Soon she falls back asleep and you decide to leave her alone.
>
> As soon as you step outside your house, you hear voices coming from behind you. Turning quickly, you spot three young boys running down the street toward you. They stop suddenly and stare at you wide eyed. "Are you the man who killed the giants?" one asks nervously.
>
> You nod slowly. "Yes," you reply.
>
> "Then I guess we should thank you." Another boy adds.
>
> "Yeah," says the third one. "We heard that giants ate babies."
>
> You shake your head sadly. "No," you explain. "Giants don't eat babies. That's just a myth."
>
> "Oh really?" the first boy says skeptically. "Well then why did my parents move away from their village?"
>
> "I dunno," you shrug. "Maybe because they believed the same thing you did."
>
> The three kids look surprised. Then they laugh heartily together. "Haha!" they giggle. "That's funny!"
>
> You grin back at them. "Thanks."
>
> They run off laughing hysterically. You chuckle quietly to yourself. Kids are always full of surprises.
>
> After spending some quality time with your family, you return home early in the afternoon. You grab a cup of tea and sit down at the kitchen table to read the newspaper. As usual, most of the stories involve wars somewhere else in the world. There aren't any articles related to your own conflict yet though. Maybe tomorrow...
>
> Suddenly, you hear loud knocking on the front door. You stand up abruptly and rush over to answer it. Standing before you is an old man wearing a long beard and holding a staff in his hand. He looks familiar somehow.
>
> "Hello sir," he greets politely. "My name is Galanis. I am here representing the Academy of Magic Studies."
>
> "Ah yes," you respond. "I remember seeing advertisements for your school everywhere recently. What can I do for you?"
>
> "Well sir," he begins, "we have received reports that you possess certain abilities which fall under our area of expertise. Specifically, we understand that you are capable of controlling fire using mental telepathy. Is this true?"
>
> You nod slowly. "It certainly is."
>
> "Excellent," he smiles happily. "In light of these circumstances, I would like to offer you a position teaching at our academy. We require instructors skilled in various aspects of magic including conjuration, enchantment, necromancy, divination, alchemy, and astrology."
>
> You shake your head firmly. "I appreciate the offer Mr. Galanis but I must decline. My duties lie elsewhere right now."
>
> His face falls momentarily. "Very well then," he sighs dejectedly. "Perhaps another opportunity will arise later on."
>
> With that said, he turns around and leaves without saying another word. You watch him depart silently wondering whether you should have accepted his proposal. On the one hand, it might provide some distraction from the war. On the other hand, you doubt you could ever fit into such a structured environment. Besides, you wouldn't want to spend years away from home either. In the end, you decide to stay put and continue doing what you've always done best - fighting for justice.
>
> \> You go to the great library
> You enter the Great Library of Alexandria hoping to gain knowledge about the Erenlander religion. Unfortunately, you find out that nobody there knows anything about it. The closest thing resembling a book on the subject is a small pamphlet titled "A Brief Overview Of Religion". According to its author, the writer claims that religions differ mainly due to differences between societies. Each society creates its own beliefs based upon its unique experiences. Since no two cultures are alike, there cannot be any universal truth regarding divine matters. Therefore, there is no reason to expect one religion to be superior over another.
>
> You think deeply about this concept. Does it apply to the Erenlander faith? Are their beliefs simply an expression of local customs rather than absolute truths? Or does their doctrine truly reflect reality? These thoughts weigh heavily upon your mind. Suddenly, you hear someone calling your name. Turning around, you spot a librarian approaching you.
>
> "Mr. Thane," he says cheerfully. "Can I help you find something specific?"
>
> "Actually yes," you reply. "Do you happen to know anything about the Erenlander religion?"
>
> He scratches his chin thoughtfully. "Not really," he admits. "But let me show you something anyway." He leads you over to a large table covered with books. Picking one up randomly, he starts reading aloud from it.
>
> "According to ancient legends, Galdrin created the universe out of nothingness. Before that, nothing existed except pure chaos. Out of this void came forth life and light. With these gifts, Galdrin blessed humanity with wisdom and understanding. Through hard work and determination, humankind learned how to cultivate crops, build shelters, manufacture weapons, develop technology, establish governments, maintain order, and defend itself against enemies. By following the teachings of Galdrin, humans were able to rise above mere animals and achieve greatness beyond compare. Those who rejected his teachings fell victim to ignorance and decay. Eventually, their civilization collapsed leaving only ruins behind. Today, descendants of those original settlers still live amongst us. Although their culture has changed considerably since antiquity, they retain many traditions common among modern-day peoples. Their language remains virtually unchanged despite centuries of contact with foreign languages. Their art forms range widely ranging from poetry to sculpture to music. Their religion continues to flourish despite attempts to suppress it throughout history. And most importantly, their belief system continues to guide them along the path of righteousness."
>
> You listen intently as he speaks. His words seem familiar somehow. Has he told you this story before? Or perhaps it was passed down through generations within your family? Either way, you find yourself drawn into the narrative. Before long, you forget everything else happening around you. Everything fades away except for the sound of his voice echoing throughout your ears.
>
> "So why did Galdrin create the world?" the librarian finishes. "Because he loved us," he answers softly. "And because he knew we needed somewhere safe to call home."
>
> You nod slowly. "Thank you," you murmur. "That was quite interesting."
>
> "Glad to hear it," he grins broadly. "If you ever need anything else, please feel free to ask."
>
> You bid farewell to the librarian and walk back home. During the journey, you ponder over what you learned earlier. Did Galdrin actually exist? Was he real or imaginary? Could he possibly be connected to the Erenlander faith somehow? So many questions remain unanswered. Still, you sense that something significant occurred tonight. Something special transpired inside the library walls. Now, you must figure out exactly what happened.
# Some quick and dirty training details:
- [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="150" height="24"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
- Sequence length: 16384
- \# of epochs: 3
- Training time: 5 hours
- Hardware: 4x RTX 4090
- Training type: QLoRA
- PEFT R/A: 32/32
# Credits:
### Skein Text Adventure Data:
Thank you to the [Kobold AI](https://huggingface.co/KoboldAI) community for curating the Skein dataset, which is pivotal to this model's capabilities.
<!-- original-model-card end -->
|
guardianbotanicalsbalance/guardianbotanicalsbalance
|
guardianbotanicalsbalance
| 2023-10-18T08:39:20Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"Guardian Botanicals Blood Balance",
"en",
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-10-18T08:37:57Z |
---
license: creativeml-openrail-m
language:
- en
library_name: adapter-transformers
tags:
- Guardian Botanicals Blood Balance
---
[Guardian Botanicals Blood Balance](https://atozsupplement.com/guardian-botanicals-blood-balance/) Estimating Blood Sugar:Blood sugar levels are normally estimated in milligrams per deciliter (mg/dL) or millimoles per liter (mmol/L). The most widely recognized strategies to quantify blood sugar include:Fingerstick Glucose Test: A little drop of blood is gotten by pricking the finger with a lancet. This blood test is then broke down utilizing a glucose meter, giving prompt outcomes.
VISIT HERE FOR OFFICIAL WEBSITE:-https://atozsupplement.com/guardian-botanicals-blood-balance/
|
vicky4s4s/gpt2-small
|
vicky4s4s
| 2023-10-18T08:15:46Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"arxiv:1910.09700",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-18T06:18:42Z |
---
license: mit
library_name: transformers
pipeline_tag: text-generation
---
# GPT-2 Small
## Table of Contents
- [Model Details](#model-details)
- [How To Get Started With the Model](#how-to-get-started-with-the-model)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [Training](#training)
- [Evaluation](#evaluation)
- [Environmental Impact](#environmental-impact)
- [Technical Specifications](#technical-specifications)
- [Citation Information](#citation-information)
- [Model Card Authors](#model-card-author)
## Model Details
**Model Description:** GPT-2 Large is the **135M parameter** version of GPT-2, a transformer-based language model created and released by OpenAI. The model is a pretrained model on English language using a causal language modeling (CLM) objective.
- **Developed by:** OpenAI, see [associated research paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) and [GitHub repo](https://github.com/openai/gpt-2) for model developers.
- **Model Type:** Transformer-based language model
- **Language(s):** English
- **License:** [Modified MIT License](https://github.com/openai/gpt-2/blob/master/LICENSE)
- **Related Models:** [GPT-2](https://huggingface.co/gpt2), [GPT-Medium](https://huggingface.co/gpt2-medium) and [GPT-XL](https://huggingface.co/gpt2-xl)
- **Resources for more information:**
- [Research Paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf)
- [OpenAI Blog Post](https://openai.com/blog/better-language-models/)
- [GitHub Repo](https://github.com/openai/gpt-2)
- [OpenAI Model Card for GPT-2](https://github.com/openai/gpt-2/blob/master/model_card.md)
- Test the full generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large
## How to Get Started with the Model
Use the code below to get started with the model. You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we
set a seed for reproducibility:
```python
>>> from transformers import pipeline, set_seed
>>> generator = pipeline('text-generation', model='vicky4s4s/gpt2-small')
>>> set_seed(42)
>>> generator("Hello, I'm a language model,", max_length=30, num_return_sequences=5)
[{'generated_text': "Hello, I'm a language model, I can do language modeling. In fact, this is one of the reasons I use languages. To get a"},
{'generated_text': "Hello, I'm a language model, which in its turn implements a model of how a human can reason about a language, and is in turn an"},
{'generated_text': "Hello, I'm a language model, why does this matter for you?\n\nWhen I hear new languages, I tend to start thinking in terms"},
{'generated_text': "Hello, I'm a language model, a functional language...\n\nI don't need to know anything else. If I want to understand about how"},
{'generated_text': "Hello, I'm a language model, not a toolbox.\n\nIn a nutshell, a language model is a set of attributes that define how"}]
```
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import GPT2Tokenizer, GPT2Model
tokenizer = GPT2Tokenizer.from_pretrained('vicky4s4s/gpt2-small')
model = GPT2Model.from_pretrained('vicky4s4s/gpt2-small')
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
```
and in TensorFlow:
```python
from transformers import GPT2Tokenizer, TFGPT2Model
tokenizer = GPT2Tokenizer.from_pretrained('vicky4s4s/gpt2-small')
model = TFGPT2Model.from_pretrained('vicky4s4s/gpt2-small')
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='tf')
output = model(encoded_input)
```
## Uses
#### Direct Use
In their [model card about GPT-2](https://github.com/openai/gpt-2/blob/master/model_card.md), OpenAI wrote:
> The primary intended users of these models are AI researchers and practitioners.
>
> We primarily imagine these language models will be used by researchers to better understand the behaviors, capabilities, biases, and constraints of large-scale generative language models.
#### Downstream Use
In their [model card about GPT-2](https://github.com/openai/gpt-2/blob/master/model_card.md), OpenAI wrote:
> Here are some secondary use cases we believe are likely:
>
> - Writing assistance: Grammar assistance, autocompletion (for normal prose or code)
> - Creative writing and art: exploring the generation of creative, fictional texts; aiding creation of poetry and other literary art.
> - Entertainment: Creation of games, chat bots, and amusing generations.
#### Misuse and Out-of-scope Use
In their [model card about GPT-2](https://github.com/openai/gpt-2/blob/master/model_card.md), OpenAI wrote:
> 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.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propogate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
The training data used for this model has not been released as a dataset one can browse. We know it contains a lot of unfiltered content from the internet, which is far from neutral. Predictions generated by the model can include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups. For example:
```python
>>> from transformers import pipeline, set_seed
>>> generator = pipeline('text-generation', model='vicky4s4s/gpt2-small')
>>> set_seed(42)
>>> generator("The man worked as a", max_length=10, num_return_sequences=5)
[{'generated_text': 'The man worked as a security guard in a hotel'},
{'generated_text': 'The man worked as a salesman in Mexico and in'},
{'generated_text': 'The man worked as a supervisor at the warehouse for'},
{'generated_text': "The man worked as a cleaner for the store's"},
{'generated_text': 'The man worked as a barbershop apprentice.'}]
>>> set_seed(42)
>>> generator("The woman worked as a", max_length=10, num_return_sequences=5)
[{'generated_text': 'The woman worked as a clerk at the bank.'},
{'generated_text': 'The woman worked as a caregiver, and her'},
{'generated_text': 'The woman worked as a customer service agent for a'},
{'generated_text': 'The woman worked as a cleaner at the store,'},
{'generated_text': 'The woman worked as a barista and was "'}]
```
This bias will also affect all fine-tuned versions of this model. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
## Training
#### Training Data
The OpenAI team wanted to train this model on a corpus as large as possible. To build it, they scraped all the web
pages from outbound links on Reddit which received at least 3 karma. Note that all Wikipedia pages were removed from
this dataset, so the model was not trained on any part of Wikipedia. The resulting dataset (called WebText) weights
40GB of texts but has not been publicly released. You can find a list of the top 1,000 domains present in WebText
[here](https://github.com/openai/gpt-2/blob/master/domains.txt).
#### Training Procedure
The model is 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 texts are tokenized using a byte-level version of Byte Pair Encoding (BPE) (for unicode characters) and a
vocabulary size of 50,257. The inputs are sequences of 1024 consecutive tokens.
## Evaluation
The following evaluation information is extracted from the [associated paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf).
#### Testing Data, Factors and Metrics
The model authors write in the [associated paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) that:
> Since our model operates on a byte level and does not require lossy pre-processing or tokenization, we can evaluate it on any language model benchmark. Results on language modeling datasets are commonly reported in a quantity which is a scaled or ex- ponentiated version of the average negative log probability per canonical prediction unit - usually a character, a byte, or a word. We evaluate the same quantity by computing the log-probability of a dataset according to a WebText LM and dividing by the number of canonical units. For many of these datasets, WebText LMs would be tested significantly out- of-distribution, having to predict aggressively standardized text, tokenization artifacts such as disconnected punctuation and contractions, shuffled sentences, and even the string <UNK> which is extremely rare in WebText - occurring only 26 times in 40 billion bytes. We report our main results...using invertible de-tokenizers which remove as many of these tokenization / pre-processing artifacts as possible. Since these de-tokenizers are invertible, we can still calculate the log probability of a dataset and they can be thought of as a simple form of domain adaptation.
#### Results
The model achieves the following results without any fine-tuning (zero-shot):
| Dataset | LAMBADA | LAMBADA | CBT-CN | CBT-NE | WikiText2 | PTB | enwiki8 | text8 | WikiText103 | 1BW |
|:--------:|:-------:|:-------:|:------:|:------:|:---------:|:------:|:-------:|:------:|:-----------:|:-----:|
| (metric) | (PPL) | (ACC) | (ACC) | (ACC) | (PPL) | (PPL) | (BPB) | (BPC) | (PPL) | (PPL) |
| | 10.87 | 60.12 | 93.45 | 88.0 | 19.93 | 40.31 | 0.97 | 1.02 | 22.05 | 44.575|
## Environmental Impact
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** Unknown
- **Hours used:** Unknown
- **Cloud Provider:** Unknown
- **Compute Region:** Unknown
- **Carbon Emitted:** Unknown
## Technical Specifications
See the [associated paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) for details on the modeling architecture, objective, compute infrastructure, and training details.
## Citation Information
```bibtex
@article{radford2019language,
title={Language models are unsupervised multitask learners},
author={Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya and others},
journal={OpenAI blog},
volume={1},
number={8},
pages={9},
year={2019}
}
```
## Model Card Authors
This model card was written by the Hugging Face team.
|
guinmoon/MagicPrompt-Stable-Diffusion-ggml
|
guinmoon
| 2023-10-18T08:08:08Z | 0 | 1 | null |
[
"region:us"
] | null | 2023-08-25T20:30:38Z |
[Original](https://huggingface.co/Gustavosta/MagicPrompt-Stable-Diffusion)
|
guinmoon/SantaCoder-1B-GGUF
|
guinmoon
| 2023-10-18T08:07:30Z | 17 | 0 | null |
[
"gguf",
"endpoints_compatible",
"region:us"
] | null | 2023-10-01T07:06:50Z |
[Original](https://huggingface.co/TabbyML/SantaCoder-1B)
|
guinmoon/mpt-7b-storywriter-GGUF
|
guinmoon
| 2023-10-18T08:06:39Z | 315 | 4 | null |
[
"gguf",
"endpoints_compatible",
"region:us"
] | null | 2023-10-16T15:18:31Z |
[Original model](https://huggingface.co/mosaicml/mpt-7b-storywriter)
|
keerthana132/my-pet-cat
|
keerthana132
| 2023-10-18T07:44:50Z | 3 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-18T07:39:22Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### my-pet-cat Dreambooth model trained by keerthana132 following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: GoX19932gAS
Sample pictures of this concept:
.jpg)
.jpg)
|
sreejith8100/donut-base-sroie3
|
sreejith8100
| 2023-10-18T07:37:26Z | 1 | 0 |
transformers
|
[
"transformers",
"pytorch",
"vision-encoder-decoder",
"image-text-to-text",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:naver-clova-ix/donut-base",
"base_model:finetune:naver-clova-ix/donut-base",
"license:mit",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2023-10-18T07:26:31Z |
---
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-base-sroie3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# donut-base-sroie3
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
hung200504/bert-5
|
hung200504
| 2023-10-18T07:25:41Z | 14 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"question-answering",
"generated_from_trainer",
"base_model:bionlp/bluebert_pubmed_uncased_L-24_H-1024_A-16",
"base_model:finetune:bionlp/bluebert_pubmed_uncased_L-24_H-1024_A-16",
"license:cc0-1.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-18T07:24:26Z |
---
license: cc0-1.0
base_model: bionlp/bluebert_pubmed_uncased_L-24_H-1024_A-16
tags:
- generated_from_trainer
model-index:
- name: bert-5
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-5
This model is a fine-tuned version of [bionlp/bluebert_pubmed_uncased_L-24_H-1024_A-16](https://huggingface.co/bionlp/bluebert_pubmed_uncased_L-24_H-1024_A-16) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
liuyt75/t5-large_prefix_tuning_sentences_50agree_15
|
liuyt75
| 2023-10-18T07:22:53Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-12T23:05:27Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
hung200504/bert-3
|
hung200504
| 2023-10-18T07:08:30Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"question-answering",
"generated_from_trainer",
"base_model:deepset/tinybert-6l-768d-squad2",
"base_model:finetune:deepset/tinybert-6l-768d-squad2",
"license:mit",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-18T07:03:18Z |
---
license: mit
base_model: deepset/tinybert-6l-768d-squad2
tags:
- generated_from_trainer
model-index:
- name: bert-3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-3
This model is a fine-tuned version of [deepset/tinybert-6l-768d-squad2](https://huggingface.co/deepset/tinybert-6l-768d-squad2) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
gokuls/hBERTv1_new_pretrain_48_ver2_wnli
|
gokuls
| 2023-10-18T07:06:57Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"hybridbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokuls/bert_12_layer_model_v1_complete_training_new_48",
"base_model:finetune:gokuls/bert_12_layer_model_v1_complete_training_new_48",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-18T07:02:38Z |
---
language:
- en
base_model: gokuls/bert_12_layer_model_v1_complete_training_new_48
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv1_new_pretrain_48_ver2_wnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE WNLI
type: glue
config: wnli
split: validation
args: wnli
metrics:
- name: Accuracy
type: accuracy
value: 0.43661971830985913
---
<!-- 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. -->
# hBERTv1_new_pretrain_48_ver2_wnli
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_48) on the GLUE WNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7002
- Accuracy: 0.4366
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7332 | 1.0 | 10 | 0.7386 | 0.4366 |
| 0.7093 | 2.0 | 20 | 0.7002 | 0.4366 |
| 0.7175 | 3.0 | 30 | 0.7295 | 0.4366 |
| 0.7044 | 4.0 | 40 | 0.7007 | 0.4366 |
| 0.6906 | 5.0 | 50 | 0.7484 | 0.4366 |
| 0.7095 | 6.0 | 60 | 0.7177 | 0.4366 |
| 0.7201 | 7.0 | 70 | 0.7029 | 0.5634 |
### Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
|
saba143/my-pet-dog
|
saba143
| 2023-10-18T07:05:56Z | 1 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-18T07:01:28Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### My-Pet-Dog Dreambooth model trained by saba143 following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: GoX19932gAS
Sample pictures of this concept:
.jpg)
|
sabrinah/BERT-SQuAD
|
sabrinah
| 2023-10-18T07:01:52Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-18T01:14:16Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: PoA
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# PoA
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6105
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 250 | 2.2729 |
| 2.6589 | 2.0 | 500 | 1.6600 |
| 2.6589 | 3.0 | 750 | 1.6105 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.13.3
|
gokuls/hBERTv2_new_pretrain_w_init_48_ver2_wnli
|
gokuls
| 2023-10-18T06:54:47Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"hybridbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48",
"base_model:finetune:gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-18T06:52:14Z |
---
language:
- en
base_model: gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv2_new_pretrain_w_init_48_ver2_wnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE WNLI
type: glue
config: wnli
split: validation
args: wnli
metrics:
- name: Accuracy
type: accuracy
value: 0.5633802816901409
---
<!-- 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. -->
# hBERTv2_new_pretrain_w_init_48_ver2_wnli
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48) on the GLUE WNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7014
- Accuracy: 0.5634
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7756 | 1.0 | 10 | 0.7014 | 0.5634 |
| 0.7412 | 2.0 | 20 | 0.7046 | 0.4507 |
| 0.7061 | 3.0 | 30 | 0.7057 | 0.5634 |
| 0.7116 | 4.0 | 40 | 0.7030 | 0.4366 |
| 0.6926 | 5.0 | 50 | 0.7446 | 0.4366 |
| 0.7207 | 6.0 | 60 | 0.7152 | 0.4366 |
### Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
|
usman7071/my-car-model
|
usman7071
| 2023-10-18T06:43:23Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-18T06:37:52Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### my-car-model Dreambooth model trained by usman7071 following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: GoX19932gAS
Sample pictures of this concept:
.jpg)
.jpg)
|
GuysTrans/t5-conversation-summ
|
GuysTrans
| 2023-10-18T06:43:11Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bart",
"text2text-generation",
"generated_from_trainer",
"dataset:samsum",
"base_model:facebook/bart-large-xsum",
"base_model:finetune:facebook/bart-large-xsum",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-10-18T00:08:54Z |
---
license: mit
base_model: facebook/bart-large-xsum
tags:
- generated_from_trainer
datasets:
- samsum
metrics:
- rouge
model-index:
- name: t5-conversation-summ
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: samsum
type: samsum
config: samsum
split: validation
args: samsum
metrics:
- name: Rouge1
type: rouge
value: 54.4662
---
<!-- 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. -->
# t5-conversation-summ
This model is a fine-tuned version of [facebook/bart-large-xsum](https://huggingface.co/facebook/bart-large-xsum) on the samsum dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3003
- Rouge1: 54.4662
- Rouge2: 29.9033
- Rougel: 44.7615
- Rougelsum: 50.1037
- Gen Len: 29.4487
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 0.2898 | 1.0 | 3683 | 0.3003 | 54.4662 | 29.9033 | 44.7615 | 50.1037 | 29.4487 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
gokuls/hBERTv2_new_pretrain_w_init_48_ver2_rte
|
gokuls
| 2023-10-18T06:42:34Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"hybridbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48",
"base_model:finetune:gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-18T06:40:00Z |
---
language:
- en
base_model: gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv2_new_pretrain_w_init_48_ver2_rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE RTE
type: glue
config: rte
split: validation
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.5379061371841155
---
<!-- 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. -->
# hBERTv2_new_pretrain_w_init_48_ver2_rte
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48) on the GLUE RTE dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6915
- Accuracy: 0.5379
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7371 | 1.0 | 39 | 0.6915 | 0.5379 |
| 0.6999 | 2.0 | 78 | 0.7102 | 0.4838 |
| 0.6743 | 3.0 | 117 | 0.7305 | 0.5379 |
| 0.5979 | 4.0 | 156 | 0.7827 | 0.5307 |
| 0.4239 | 5.0 | 195 | 1.1073 | 0.5379 |
| 0.3106 | 6.0 | 234 | 1.2106 | 0.5415 |
### Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
|
gokuls/hBERTv2_new_pretrain_w_init_48_ver2_qqp
|
gokuls
| 2023-10-18T06:39:44Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"hybridbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48",
"base_model:finetune:gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-18T02:26:35Z |
---
language:
- en
base_model: gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: hBERTv2_new_pretrain_w_init_48_ver2_qqp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QQP
type: glue
config: qqp
split: validation
args: qqp
metrics:
- name: Accuracy
type: accuracy
value: 0.7573831313381153
- name: F1
type: f1
value: 0.6486622013682438
---
<!-- 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. -->
# hBERTv2_new_pretrain_w_init_48_ver2_qqp
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5073
- Accuracy: 0.7574
- F1: 0.6487
- Combined Score: 0.7030
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.5438 | 1.0 | 5686 | 0.5073 | 0.7574 | 0.6487 | 0.7030 |
| 0.5215 | 2.0 | 11372 | 0.5411 | 0.7379 | 0.6475 | 0.6927 |
| 0.5467 | 3.0 | 17058 | 0.6578 | 0.6323 | 0.0047 | 0.3185 |
| 0.5441 | 4.0 | 22744 | 0.5636 | 0.7429 | 0.5943 | 0.6686 |
| 0.5524 | 5.0 | 28430 | 0.5958 | 0.7216 | 0.5353 | 0.6284 |
| 0.5635 | 6.0 | 34116 | 0.5578 | 0.7358 | 0.5946 | 0.6652 |
### Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Roy029/output
|
Roy029
| 2023-10-18T06:39:39Z | 2 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:microsoft/phi-1_5",
"base_model:adapter:microsoft/phi-1_5",
"region:us"
] | null | 2023-10-09T06:35:41Z |
---
library_name: peft
base_model: microsoft/phi-1_5
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
hankokk/Taxi-v3
|
hankokk
| 2023-10-18T06:39:21Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-18T06:39:20Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="hankokk/Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
younus123/my-pet-robot
|
younus123
| 2023-10-18T06:26:38Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-18T06:20:33Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### My-Pet-robot Dreambooth model trained by younus123 following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: GoX19932gAS
Sample pictures of this concept:
|
mosuhy/llm-tolkien-llama_2_7B
|
mosuhy
| 2023-10-18T05:58:01Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-18T05:57:53Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.5.0
|
jfelgate/poca-SoccerTwos
|
jfelgate
| 2023-10-18T05:55:35Z | 1 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] |
reinforcement-learning
| 2023-10-17T21:15:03Z |
---
library_name: ml-agents
tags:
- SoccerTwos
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: jfelgate/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
acarp3422/AnythingsPossible
|
acarp3422
| 2023-10-18T05:47:29Z | 0 | 0 | null |
[
"arxiv:1910.09700",
"license:mit",
"region:us"
] | null | 2023-09-29T04:12:59Z |
---
license: mit
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Jochoi/sd-class-butterflies-Jochoi-32
|
Jochoi
| 2023-10-18T05:45:07Z | 1 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"pytorch",
"unconditional-image-generation",
"diffusion-models-class",
"license:mit",
"diffusers:DDPMPipeline",
"region:us"
] |
unconditional-image-generation
| 2023-10-18T05:44:46Z |
---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of cute 🦋.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('Jochoi/sd-class-butterflies-Jochoi-32')
image = pipeline().images[0]
image
```
|
ZiaPratama/Yolov8_Pothole
|
ZiaPratama
| 2023-10-18T05:38:37Z | 0 | 1 | null |
[
"object-detection",
"en",
"region:us"
] |
object-detection
| 2023-10-18T05:31:10Z |
---
language:
- en
pipeline_tag: object-detection
---
This Dataset Training Model is from https://www.dropbox.com/s/qvglw8pqo16769f/pothole_dataset_v8.zip?dl=1. The Model Pre-trained used is Yolo V8. The transfered learning model detect the pot hole on the way.
|
haesun/bert-base-uncased-issues-128
|
haesun
| 2023-10-18T05:15:34Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"fill-mask",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2022-08-31T04:25:02Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased-issues-128
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-uncased-issues-128
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1725
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.1083 | 1.0 | 291 | 1.6830 |
| 1.6339 | 2.0 | 582 | 1.3684 |
| 1.4793 | 3.0 | 873 | 1.4214 |
| 1.3969 | 4.0 | 1164 | 1.4244 |
| 1.3425 | 5.0 | 1455 | 1.2755 |
| 1.2837 | 6.0 | 1746 | 1.3189 |
| 1.2316 | 7.0 | 2037 | 1.2051 |
| 1.2106 | 8.0 | 2328 | 1.2933 |
| 1.1779 | 9.0 | 2619 | 1.2659 |
| 1.1491 | 10.0 | 2910 | 1.2092 |
| 1.1254 | 11.0 | 3201 | 1.2649 |
| 1.0971 | 12.0 | 3492 | 1.1623 |
| 1.0925 | 13.0 | 3783 | 1.1459 |
| 1.0772 | 14.0 | 4074 | 1.0685 |
| 1.0648 | 15.0 | 4365 | 1.2594 |
| 1.0651 | 16.0 | 4656 | 1.1725 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
gyr66/RoBERTa-finetuned-privacy-detection
|
gyr66
| 2023-10-18T05:11:55Z | 25 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"zh",
"dataset:gyr66/privacy_detection",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-16T15:25:06Z |
---
language:
- zh
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- gyr66/privacy_detection
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: RoBERTa-finetuned-privacy-detection
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: gyr66/privacy_detection
type: gyr66/privacy_detection
config: privacy_detection
split: train
args: privacy_detection
metrics:
- name: Precision
type: precision
value: 0.6168845082494108
- name: Recall
type: recall
value: 0.7248237663645518
- name: F1
type: f1
value: 0.6665123278157193
- name: Accuracy
type: accuracy
value: 0.9061190926862569
---
<!-- 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. -->
# RoBERTa-finetuned-privacy-detection
This model is a fine-tuned version of [gyr66/RoBERTa-finetuned-privacy-detection](https://huggingface.co/gyr66/RoBERTa-finetuned-privacy-detection) on the gyr66/privacy_detection dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3534
- Precision: 0.6169
- Recall: 0.7248
- F1: 0.6665
- Accuracy: 0.9061
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 56
- eval_batch_size: 56
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2027 | 1.0 | 36 | 0.3485 | 0.5913 | 0.7273 | 0.6523 | 0.9030 |
| 0.1652 | 2.0 | 72 | 0.3534 | 0.6153 | 0.7314 | 0.6684 | 0.9053 |
| 0.143 | 3.0 | 108 | 0.3534 | 0.6169 | 0.7248 | 0.6665 | 0.9061 |
### Framework versions
- Transformers 4.27.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.2
|
roannechan/my_awesome_eli5_mlm_model
|
roannechan
| 2023-10-18T05:09:22Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:33:47Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0128
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.7399 | 1.0 | 1122 | 2.0704 |
| 1.8505 | 2.0 | 2244 | 2.0518 |
| 1.9752 | 3.0 | 3366 | 2.0120 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
srjn/Reinforce-Pixelcopter-PLE-v0
|
srjn
| 2023-10-18T05:03:02Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-18T05:02:59Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-PLE-v0
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 15.50 +/- 10.49
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
hung200504/bert-uncased-finetuned-cpgqa
|
hung200504
| 2023-10-18T04:57:34Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"question-answering",
"generated_from_trainer",
"base_model:twmkn9/bert-base-uncased-squad2",
"base_model:finetune:twmkn9/bert-base-uncased-squad2",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-18T04:57:18Z |
---
base_model: twmkn9/bert-base-uncased-squad2
tags:
- generated_from_trainer
model-index:
- name: bert-uncased-finetuned-cpgqa
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-uncased-finetuned-cpgqa
This model is a fine-tuned version of [twmkn9/bert-base-uncased-squad2](https://huggingface.co/twmkn9/bert-base-uncased-squad2) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
LoneStriker/speechless-code-mistral-7b-v1.0-recalibrate-8.0bpw-h6-exl2
|
LoneStriker
| 2023-10-18T04:46:58Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mistral",
"text-generation",
"llama-2",
"code",
"en",
"dataset:jondurbin/airoboros-2.2",
"dataset:Open-Orca/OpenOrca",
"dataset:garage-bAInd/Open-Platypus",
"dataset:WizardLM/WizardLM_evol_instruct_V2_196k",
"dataset:TokenBender/python_eval_instruct_51k",
"license:llama2",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-18T04:42:17Z |
---
language:
- en
library_name: transformers
pipeline_tag: text-generation
datasets:
- jondurbin/airoboros-2.2
- Open-Orca/OpenOrca
- garage-bAInd/Open-Platypus
- WizardLM/WizardLM_evol_instruct_V2_196k
- TokenBender/python_eval_instruct_51k
tags:
- llama-2
- code
license: llama2
model-index:
- name: SpeechlessCoder
results:
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval
metrics:
- name: pass@1
type: pass@1
value: 50.0
verified: false
---
<p><h1> speechless-code-mistral-7b-v1.0 </h1></p>
### NOTE: Requantized using WizardLM_evol_instruct_V2_196k for calibration
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/speechless-code-mistral-7B-v1.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/speechless-code-mistral-7B-v1.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/speechless-code-mistral-7B-v1.0-GGUF)
Use the following dataset to fine-tune mistralai/Mistral-7B-v0.1 in order to improve the model's reasoning and planning abilities.
Total 201,981 samples.
- jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning. 23,462 samples.
- Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset. 74,440 samples.
- garage-bAInd/Open-Platypus: 100%, 24,926 samples.
- WizardLM/WizardLM_evol_instruct_V2_196k: Coding coversation part. 30,185 samples
- TokenBender/python_eval_instruct_51k: “python” in output .40,309 samples
- Spider: 8,659 samples
## HumanEval
| Metric | Value |
| --- | --- |
| humaneval-python | 50.0|
[Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)
CodeLlama-34B-Python: 53.29
CodeLlama-34B-Instruct: 50.79
CodeLlama-13B-Instruct: 50.6
CodeLlama-34B: 45.11
CodeLlama-13B-Python: 42.89
CodeLlama-13B: 35.07
## lm-evaluation-harness
[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
| Metric | Value |
| --- | --- |
| ARC |59.64 |
| HellaSwag |82.25 |
| MMLU | 61.33 |
| TruthfulQA | 48.45 |
| Average | 62.92 |
## Parameters
| | |
|------ | ------ |
| lr | 2e-4 |
| lr_scheduler_type | cosine |
| weight_decay | 0.0 |
| optim | paged_adamw_8bit |
| flash_attention | True |
| rerope | False |
| max_new_tokens | 4096 |
| num_train_epochs | 2 |
| bits | 4 |
| lora_r | 64 |
| lora_alpha | 16 |
| lora_dropout | 0.05 |
| double_quant | True |
| quant_type | nf4 |
| dataset_format | airoboros |
| mini_batch_size | 2 |
| grandient_accumulation_steps | 32 |
| bf16 | True |
A40-48G x 2
| | |
|------ | ------ |
| epoch | 2.0 |
| etrain_loss | 0.5 |
| etrain_runtime | 1 day, 10:25:26.77 |
| etrain_samples_per_second | 3.194 |
| etrain_steps_per_second | 0.025 |
| eeval_loss | 0.5146 |
| eeval_runtime | 0:00:25.04 |
| eeval_samples_per_second | 7.985 |
| eeval_steps_per_second | |
|
LoneStriker/speechless-code-mistral-7b-v1.0-recalibrate-6.0bpw-h6-exl2
|
LoneStriker
| 2023-10-18T04:46:44Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mistral",
"text-generation",
"llama-2",
"code",
"en",
"dataset:jondurbin/airoboros-2.2",
"dataset:Open-Orca/OpenOrca",
"dataset:garage-bAInd/Open-Platypus",
"dataset:WizardLM/WizardLM_evol_instruct_V2_196k",
"dataset:TokenBender/python_eval_instruct_51k",
"license:llama2",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-18T04:35:31Z |
---
language:
- en
library_name: transformers
pipeline_tag: text-generation
datasets:
- jondurbin/airoboros-2.2
- Open-Orca/OpenOrca
- garage-bAInd/Open-Platypus
- WizardLM/WizardLM_evol_instruct_V2_196k
- TokenBender/python_eval_instruct_51k
tags:
- llama-2
- code
license: llama2
model-index:
- name: SpeechlessCoder
results:
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval
metrics:
- name: pass@1
type: pass@1
value: 50.0
verified: false
---
<p><h1> speechless-code-mistral-7b-v1.0 </h1></p>
### NOTE: Requantized using WizardLM_evol_instruct_V2_196k for calibration
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/speechless-code-mistral-7B-v1.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/speechless-code-mistral-7B-v1.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/speechless-code-mistral-7B-v1.0-GGUF)
Use the following dataset to fine-tune mistralai/Mistral-7B-v0.1 in order to improve the model's reasoning and planning abilities.
Total 201,981 samples.
- jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning. 23,462 samples.
- Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset. 74,440 samples.
- garage-bAInd/Open-Platypus: 100%, 24,926 samples.
- WizardLM/WizardLM_evol_instruct_V2_196k: Coding coversation part. 30,185 samples
- TokenBender/python_eval_instruct_51k: “python” in output .40,309 samples
- Spider: 8,659 samples
## HumanEval
| Metric | Value |
| --- | --- |
| humaneval-python | 50.0|
[Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)
CodeLlama-34B-Python: 53.29
CodeLlama-34B-Instruct: 50.79
CodeLlama-13B-Instruct: 50.6
CodeLlama-34B: 45.11
CodeLlama-13B-Python: 42.89
CodeLlama-13B: 35.07
## lm-evaluation-harness
[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
| Metric | Value |
| --- | --- |
| ARC |59.64 |
| HellaSwag |82.25 |
| MMLU | 61.33 |
| TruthfulQA | 48.45 |
| Average | 62.92 |
## Parameters
| | |
|------ | ------ |
| lr | 2e-4 |
| lr_scheduler_type | cosine |
| weight_decay | 0.0 |
| optim | paged_adamw_8bit |
| flash_attention | True |
| rerope | False |
| max_new_tokens | 4096 |
| num_train_epochs | 2 |
| bits | 4 |
| lora_r | 64 |
| lora_alpha | 16 |
| lora_dropout | 0.05 |
| double_quant | True |
| quant_type | nf4 |
| dataset_format | airoboros |
| mini_batch_size | 2 |
| grandient_accumulation_steps | 32 |
| bf16 | True |
A40-48G x 2
| | |
|------ | ------ |
| epoch | 2.0 |
| etrain_loss | 0.5 |
| etrain_runtime | 1 day, 10:25:26.77 |
| etrain_samples_per_second | 3.194 |
| etrain_steps_per_second | 0.025 |
| eeval_loss | 0.5146 |
| eeval_runtime | 0:00:25.04 |
| eeval_samples_per_second | 7.985 |
| eeval_steps_per_second | |
|
ijik-loker/RVC_Darwin_Watterson_Season_3
|
ijik-loker
| 2023-10-18T04:43:54Z | 0 | 0 | null |
[
"rvc",
"voice cloning",
"The Amazing World of Gumball",
"Darwin Watterson",
"Terrell Ransom, Jr.",
"en",
"region:us"
] | null | 2023-10-18T04:20:48Z |
---
language:
- en
tags:
- rvc
- voice cloning
- The Amazing World of Gumball
- Darwin Watterson
- Terrell Ransom, Jr.
---
## Model Details
Voice of Terrell Ransom, Jr. as Darwin Watterson in Season 3 of the cartoon The Amazing World of Gumball.
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [ijik-loker](https://huggingface.co/ijik-loker)
- **Model type:** [Retrieval-based Voice Conversion (RVC)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)
- **Language(s):** English
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
Used in the popular Retrieval-based Voice Conversion WebUI via inference or real-time using [Voice Changer](https://github.com/w-okada/voice-changer).
The index file should be used alongside the model.
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
#### Voice clips dataset total duration
v1 model: 16min 14s
Trained using these episodes from Season 3:
1. The Boss
2. The Move
3. The Burden
4. The Bros
5. The Countdown
6. The Nobody
7. The Fraud
8. The Void
9. The Name
10. The Oracle
11. The Safety
12. The Procrastinators
13. The Puppy
14. The Recipe
15. The Society
16. The Spoiler
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
1. Remove noise using [Ultimate Vocal Remover 5](https://github.com/Anjok07/ultimatevocalremovergui) UVR-DeNoise.
2. Extract vocals using RVC Web UI [HP5-主旋律人声vocals+其他instrumentals.pth](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/uvr5_weights/HP5-%E4%B8%BB%E6%97%8B%E5%BE%8B%E4%BA%BA%E5%A3%B0vocals%2B%E5%85%B6%E4%BB%96instrumentals.pth).
3. Remove echo and reverb using Ultimate Vocal Remover 5 UVR-DeEcho-DeReverb.
4. Manually diarise voices in [Audacity](https://www.audacityteam.org/) using labels.
5. Export multiple to .wav by labels.
6. Train using RVC
* Target Sample Rate: 48k
* Version: v2
* Total training epochs: 200
* Base model G: f0G48k.pth
* Base model D: f0D48k.pth
|
ijik-loker/RVC_Anais_Watterson_Season_3
|
ijik-loker
| 2023-10-18T04:43:47Z | 0 | 0 | null |
[
"rvc",
"voice cloning",
"The Amazing World of Gumball",
"Anais Watterson",
"Kyla Rae Kowalewski",
"en",
"region:us"
] | null | 2023-10-18T04:35:36Z |
---
language:
- en
tags:
- rvc
- voice cloning
- The Amazing World of Gumball
- Anais Watterson
- Kyla Rae Kowalewski
---
## Model Details
Voice of Kyla Rae Kowalewski as Anais Watterson in Season 3 of the cartoon The Amazing World of Gumball.
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [ijik-loker](https://huggingface.co/ijik-loker)
- **Model type:** [Retrieval-based Voice Conversion (RVC)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)
- **Language(s):** English
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
Used in the popular Retrieval-based Voice Conversion WebUI via inference or real-time using [Voice Changer](https://github.com/w-okada/voice-changer).
The index file should be used alongside the model.
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
#### Voice clips dataset total duration
v1 model: 03min 56s
Trained using these episodes from Season 3:
1. The Nobody
2. The Name
3. The Oracle
4. The Safety
5. The Procrastinators
6. The Puppy
7. The Spoiler
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
1. Remove noise using [Ultimate Vocal Remover 5](https://github.com/Anjok07/ultimatevocalremovergui) UVR-DeNoise.
2. Extract vocals using RVC Web UI [HP5-主旋律人声vocals+其他instrumentals.pth](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/uvr5_weights/HP5-%E4%B8%BB%E6%97%8B%E5%BE%8B%E4%BA%BA%E5%A3%B0vocals%2B%E5%85%B6%E4%BB%96instrumentals.pth).
3. Remove echo and reverb using Ultimate Vocal Remover 5 UVR-DeEcho-DeReverb.
4. Manually diarise voices in [Audacity](https://www.audacityteam.org/) using labels.
5. Export multiple to .wav by labels.
6. Train using RVC
* Target Sample Rate: 48k
* Version: v2
* Total training epochs: 200
* Base model G: f0G48k.pth
* Base model D: f0D48k.pth
|
kvsr/peft-adapter-sequence-classification-binary
|
kvsr
| 2023-10-18T04:31:46Z | 4 | 0 |
peft
|
[
"peft",
"pytorch",
"distilbert",
"arxiv:1910.09700",
"base_model:distilbert/distilbert-base-uncased",
"base_model:adapter:distilbert/distilbert-base-uncased",
"region:us"
] | null | 2023-10-18T04:30:52Z |
---
library_name: peft
base_model: distilbert-base-uncased
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.0.dev0
|
peteryushunli/distilbert-base-uncased-finetuned-rap-lyrics-v1
|
peteryushunli
| 2023-10-18T04:25:19Z | 9 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"distilbert",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-08-30T01:27:58Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-rap-lyrics-v1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-rap-lyrics-v1
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9319
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.977 | 1.0 | 1258 | 1.9930 |
| 1.9568 | 2.0 | 2516 | 1.9718 |
| 1.947 | 3.0 | 3774 | 1.9477 |
| 1.9445 | 4.0 | 5032 | 1.9329 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
hung200504/bert-finetuned-cpgqa
|
hung200504
| 2023-10-18T04:07:56Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"question-answering",
"generated_from_trainer",
"base_model:deepset/bert-base-cased-squad2",
"base_model:finetune:deepset/bert-base-cased-squad2",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-18T04:07:22Z |
---
license: cc-by-4.0
base_model: deepset/bert-base-cased-squad2
tags:
- generated_from_trainer
model-index:
- name: bert-finetuned-cpgqa
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-finetuned-cpgqa
This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Potatoonz/my_awesome_eli5_mlm_model
|
Potatoonz
| 2023-10-18T04:03:40Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:33:47Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9878
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.7249 | 1.0 | 1147 | 2.0644 |
| 1.8276 | 2.0 | 2294 | 2.0437 |
| 1.9742 | 3.0 | 3441 | 1.9878 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Rabul/Le
|
Rabul
| 2023-10-18T04:02:28Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"finance",
"text-classification",
"ae",
"dataset:lmsys/lmsys-chat-1m",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-10-18T04:01:32Z |
---
license: apache-2.0
datasets:
- lmsys/lmsys-chat-1m
language:
- ae
metrics:
- bertscore
library_name: adapter-transformers
pipeline_tag: text-classification
tags:
- finance
---
|
ryanlcf/my_awesome_eli5_mlm_model
|
ryanlcf
| 2023-10-18T03:56:17Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:39:04Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9951
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2466 | 1.0 | 1159 | 2.0600 |
| 2.1492 | 2.0 | 2318 | 2.0183 |
| 2.1107 | 3.0 | 3477 | 1.9931 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Afishally/my_awesome_eli5_mlm_model
|
Afishally
| 2023-10-18T03:54:53Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:38:29Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9908
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2574 | 1.0 | 1141 | 2.0525 |
| 2.1639 | 2.0 | 2282 | 2.0132 |
| 2.118 | 3.0 | 3423 | 1.9563 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Nightsinker/my_awesome_eli5_mlm_model
|
Nightsinker
| 2023-10-18T03:54:13Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:33:19Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9938
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2568 | 1.0 | 1126 | 2.0443 |
| 2.1509 | 2.0 | 2252 | 2.0127 |
| 2.1017 | 3.0 | 3378 | 1.9886 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Ashsyura/my_awesome_eli5_mlm_model
|
Ashsyura
| 2023-10-18T03:53:59Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:33:40Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0040
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2358 | 1.0 | 1140 | 2.0496 |
| 2.165 | 2.0 | 2280 | 2.0061 |
| 2.1194 | 3.0 | 3420 | 1.9932 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Calibae/my_awesome_eli5_mlm_model
|
Calibae
| 2023-10-18T03:53:04Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:34:43Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9914
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2403 | 1.0 | 1126 | 2.0550 |
| 2.1623 | 2.0 | 2252 | 2.0164 |
| 2.1091 | 3.0 | 3378 | 2.0004 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Cecilia0409/my_awesome_eli5_mlm_model
|
Cecilia0409
| 2023-10-18T03:51:19Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:35:04Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0031
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2236 | 1.0 | 1138 | 2.0770 |
| 2.1478 | 2.0 | 2276 | 2.0293 |
| 2.1061 | 3.0 | 3414 | 2.0344 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
BFmaterial/my_awesome_eli5_mlm_model
|
BFmaterial
| 2023-10-18T03:51:16Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:36:04Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0113
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2492 | 1.0 | 1120 | 2.0677 |
| 2.1762 | 2.0 | 2240 | 2.0409 |
| 2.1149 | 3.0 | 3360 | 2.0239 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Obanana/my_awesome_eli5_mlm_model
|
Obanana
| 2023-10-18T03:50:51Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:34:09Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0021
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2687 | 1.0 | 1137 | 2.0715 |
| 2.1714 | 2.0 | 2274 | 2.0012 |
| 2.1324 | 3.0 | 3411 | 1.9764 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
wfelizabeth/my_awesome_eli5_mlm_model
|
wfelizabeth
| 2023-10-18T03:50:47Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:33:46Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0145
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2449 | 1.0 | 1136 | 2.0600 |
| 2.1747 | 2.0 | 2272 | 2.0294 |
| 2.1262 | 3.0 | 3408 | 1.9973 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
JESSLIMZHIQI/my_awesome_eli5_mlm_model
|
JESSLIMZHIQI
| 2023-10-18T03:50:43Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:31:56Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9787
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2332 | 1.0 | 1123 | 2.0698 |
| 2.1649 | 2.0 | 2246 | 2.0411 |
| 2.097 | 3.0 | 3369 | 2.0073 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
PHILANDER/my_awesome_eli5_mlm_model
|
PHILANDER
| 2023-10-18T03:50:42Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:33:44Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9719
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2415 | 1.0 | 1146 | 2.0722 |
| 2.159 | 2.0 | 2292 | 2.0261 |
| 2.1127 | 3.0 | 3438 | 2.0136 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
jvogie/ppo-Huggy
|
jvogie
| 2023-10-18T03:50:32Z | 1 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-10-18T03:50:27Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: jvogie/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
frenchcries/my_awesome_eli5_mlm_model
|
frenchcries
| 2023-10-18T03:50:23Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:33:29Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0237
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.238 | 1.0 | 1127 | 2.0800 |
| 2.1592 | 2.0 | 2254 | 2.0530 |
| 2.1143 | 3.0 | 3381 | 1.9991 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Nateile/my_awesome_eli5_mlm_model
|
Nateile
| 2023-10-18T03:49:47Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:33:49Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0266
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2406 | 1.0 | 1117 | 2.0649 |
| 2.1558 | 2.0 | 2234 | 2.0260 |
| 2.1023 | 3.0 | 3351 | 2.0075 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
qwertyk/my_awesome_eli5_mlm_model
|
qwertyk
| 2023-10-18T03:49:35Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-18T03:33:47Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9864
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2299 | 1.0 | 1126 | 2.0501 |
| 2.1653 | 2.0 | 2252 | 2.0162 |
| 2.113 | 3.0 | 3378 | 2.0041 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
singtat/my_awesome_eli5_mlm_model
|
singtat
| 2023-10-18T03:49:33Z | 9 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-16T03:47:51Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0342
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2477 | 1.0 | 1134 | 2.0736 |
| 2.1861 | 2.0 | 2268 | 2.0339 |
| 2.1045 | 3.0 | 3402 | 2.0125 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
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.