modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-12 00:41:42
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 555
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-12 00:40:24
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
sail-rvc/Amamiya_Sora
|
sail-rvc
| 2023-07-14T07:18:25Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:55Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Amamiya_Sora
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:25
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Aghatanunes500epochs
|
sail-rvc
| 2023-07-14T07:18:24Z | 2 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:53Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Aghatanunes500epochs
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:24
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Anuvmodel
|
sail-rvc
| 2023-07-14T07:18:23Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:59Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Anuvmodel
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:23
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Autumn
|
sail-rvc
| 2023-07-14T07:18:23Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:18:10Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Autumn
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:22
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Angie
|
sail-rvc
| 2023-07-14T07:18:23Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:55Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Angie
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:23
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Alejo_Isakk__RVC_V2__Harvest__-_300_Epochs_
|
sail-rvc
| 2023-07-14T07:18:22Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:45Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Alejo_Isakk__RVC_V2__Harvest__-_300_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:22
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AnthonyPadilla_PatrickNeluam__RVCV2_Harvest_-200Epochs_
|
sail-rvc
| 2023-07-14T07:18:22Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:18:12Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AnthonyPadilla_PatrickNeluam__RVCV2_Harvest_-200Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:22
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Asta2333333
|
sail-rvc
| 2023-07-14T07:18:20Z | 2 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:18:05Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Asta2333333
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:20
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AmaIA22333333
|
sail-rvc
| 2023-07-14T07:18:18Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:58Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AmaIA22333333
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:18
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AlbertFlamingo_e260_s34320
|
sail-rvc
| 2023-07-14T07:18:17Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:56Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AlbertFlamingo_e260_s34320
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:17
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Anthonycraft
|
sail-rvc
| 2023-07-14T07:18:16Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:58Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Anthonycraft
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:16
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Anasui2333333
|
sail-rvc
| 2023-07-14T07:18:15Z | 2 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:18:01Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Anasui2333333
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:15
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Anthonycraft2333333
|
sail-rvc
| 2023-07-14T07:18:15Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:57Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Anthonycraft2333333
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:15
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Alyx_Vance_500
|
sail-rvc
| 2023-07-14T07:18:12Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:50Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Alyx_Vance_500
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:12
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Arona
|
sail-rvc
| 2023-07-14T07:18:12Z | 4 | 1 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:18:02Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Arona
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:12
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Arana__Minecraft___RVC_V2_-_150_Epochs_
|
sail-rvc
| 2023-07-14T07:18:11Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:18:00Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Arana__Minecraft___RVC_V2_-_150_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:11
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Andersen
|
sail-rvc
| 2023-07-14T07:18:11Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:52Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Andersen
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:11
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Aatrox
|
sail-rvc
| 2023-07-14T07:18:11Z | 3 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:26Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Aatrox
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:11
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AngelDust_e240
|
sail-rvc
| 2023-07-14T07:18:10Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:56Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AngelDust_e240
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:10
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AngelaLoR
|
sail-rvc
| 2023-07-14T07:18:10Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:56Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AngelaLoR
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:10
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AlexTurner
|
sail-rvc
| 2023-07-14T07:18:09Z | 167 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:52Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AlexTurner
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:08
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Amber_1
|
sail-rvc
| 2023-07-14T07:18:09Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:56Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Amber_1
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:09
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AlexMason
|
sail-rvc
| 2023-07-14T07:18:08Z | 1 | 1 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:43Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AlexMason
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:08
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Alduin
|
sail-rvc
| 2023-07-14T07:18:04Z | 1 | 1 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:43Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Alduin
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:04
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/69v2
|
sail-rvc
| 2023-07-14T07:18:03Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:28Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# 69v2
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:03
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AlecchiMan__RVC_V2__Harvest__-_200_Epochs_
|
sail-rvc
| 2023-07-14T07:17:58Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:43Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AlecchiMan__RVC_V2__Harvest__-_200_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:58
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Aldeano_Minecraft__RVC_V2_-_500_Epochs_
|
sail-rvc
| 2023-07-14T07:17:58Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:46Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Aldeano_Minecraft__RVC_V2_-_500_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:58
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Alisa
|
sail-rvc
| 2023-07-14T07:17:57Z | 3 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:44Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Alisa
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:57
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AK_420__RVC_V2__Crepe_64__-_250_Epochs_
|
sail-rvc
| 2023-07-14T07:17:57Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:27Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AK_420__RVC_V2__Crepe_64__-_250_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:57
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Alucard
|
sail-rvc
| 2023-07-14T07:17:56Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:43Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Alucard
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:56
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Akane_model
|
sail-rvc
| 2023-07-14T07:17:56Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:31Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Akane_model
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:56
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Alia-Tigress
|
sail-rvc
| 2023-07-14T07:17:56Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:44Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Alia-Tigress
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:56
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/2m_e650_s7800
|
sail-rvc
| 2023-07-14T07:17:53Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:30Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# 2m_e650_s7800
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:53
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Adrian_Barba__RVC_-_500_Epochs_
|
sail-rvc
| 2023-07-14T07:17:51Z | 2 | 1 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:30Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Adrian_Barba__RVC_-_500_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:50
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AbueloRVCModel
|
sail-rvc
| 2023-07-14T07:17:51Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:30Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AbueloRVCModel
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:51
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Agustin51__RVC_V2__Harvest__-_200_Epochs_
|
sail-rvc
| 2023-07-14T07:17:50Z | 2 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:26Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Agustin51__RVC_V2__Harvest__-_200_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:50
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AiHoshino
|
sail-rvc
| 2023-07-14T07:17:50Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:27Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AiHoshino
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:50
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
Mayypeeya/my_thaisum_model
|
Mayypeeya
| 2023-07-14T07:17:50Z | 22 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"t5",
"text2text-generation",
"generated_from_trainer",
"dataset:thaisum",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-07-14T05:53:11Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- thaisum
metrics:
- rouge
model-index:
- name: my_thaisum_model
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: thaisum
type: thaisum
config: thaisum
split: validation
args: thaisum
metrics:
- name: Rouge1
type: rouge
value: 0.0808
---
<!-- 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_thaisum_model
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the thaisum dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2693
- Rouge1: 0.0808
- Rouge2: 0.0381
- Rougel: 0.0803
- Rougelsum: 0.0803
- Gen Len: 18.9585
## 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: 4
- eval_batch_size: 4
- 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 0.565 | 1.0 | 2500 | 0.2799 | 0.0605 | 0.0231 | 0.0599 | 0.0598 | 18.976 |
| 0.3769 | 2.0 | 5000 | 0.2693 | 0.0808 | 0.0381 | 0.0803 | 0.0803 | 18.9585 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
sail-rvc/2018carti
|
sail-rvc
| 2023-07-14T07:17:50Z | 7 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:26Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# 2018carti
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:50
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/1mms
|
sail-rvc
| 2023-07-14T07:17:48Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:32Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# 1mms
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:48
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Abel_Pintos__RVC_-_1000_Epochs_
|
sail-rvc
| 2023-07-14T07:17:47Z | 3 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:26Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Abel_Pintos__RVC_-_1000_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:47
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AOAseolhyun
|
sail-rvc
| 2023-07-14T07:17:46Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:26Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AOAseolhyun
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:46
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Ai_Hoshino__From_Oshi_no_Ko___RVC_v2__300_Epoch
|
sail-rvc
| 2023-07-14T07:17:46Z | 2 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:28Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Ai_Hoshino__From_Oshi_no_Ko___RVC_v2__300_Epoch
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:46
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Alecs
|
sail-rvc
| 2023-07-14T07:17:44Z | 2 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:31Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Alecs
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:44
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Akane_Kurokawa__RVC_V2_-_500_Epochs_
|
sail-rvc
| 2023-07-14T07:17:43Z | 6 | 1 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:30Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Akane_Kurokawa__RVC_V2_-_500_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:43
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AARON
|
sail-rvc
| 2023-07-14T07:17:43Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:27Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AARON
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:43
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/6LACK__RVC_-_700_Epochs_
|
sail-rvc
| 2023-07-14T07:17:43Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:30Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# 6LACK__RVC_-_700_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:43
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AkiX2333333
|
sail-rvc
| 2023-07-14T07:17:42Z | 2 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:31Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AkiX2333333
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:42
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Akira2333333
|
sail-rvc
| 2023-07-14T07:17:42Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:29Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Akira2333333
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:42
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Akechi
|
sail-rvc
| 2023-07-14T07:17:41Z | 1 | 1 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:29Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Akechi
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:41
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/AeonAir
|
sail-rvc
| 2023-07-14T07:17:41Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:30Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AeonAir
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:41
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Aitana__RVC_V1_-_500_Epochs_
|
sail-rvc
| 2023-07-14T07:17:41Z | 1 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:28Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Aitana__RVC_V1_-_500_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:41
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/2NE1parkbom
|
sail-rvc
| 2023-07-14T07:17:40Z | 3 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:24Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# 2NE1parkbom
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:40
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
sail-rvc/Adolf_Hitler__RVC_v2_
|
sail-rvc
| 2023-07-14T07:17:40Z | 4 | 0 |
transformers
|
[
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
] |
audio-to-audio
| 2023-07-14T07:17:28Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Adolf_Hitler__RVC_v2_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:40
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
NasimB/gpt2-concat-all-base-rarity-all-iorder-8k
|
NasimB
| 2023-07-14T07:12:46Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:generator",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-14T05:17:08Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-concat-all-base-rarity-all-iorder-8k
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. -->
# gpt2-concat-all-base-rarity-all-iorder-8k
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 4.3668
## 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: 0.0005
- 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: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 7
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.7674 | 0.31 | 500 | 5.6574 |
| 5.4175 | 0.63 | 1000 | 5.2219 |
| 5.0586 | 0.94 | 1500 | 4.9730 |
| 4.769 | 1.25 | 2000 | 4.8188 |
| 4.6293 | 1.57 | 2500 | 4.6974 |
| 4.5229 | 1.88 | 3000 | 4.5900 |
| 4.32 | 2.19 | 3500 | 4.5361 |
| 4.2339 | 2.51 | 4000 | 4.4732 |
| 4.1839 | 2.82 | 4500 | 4.4075 |
| 4.048 | 3.13 | 5000 | 4.3910 |
| 3.9138 | 3.45 | 5500 | 4.3635 |
| 3.913 | 3.76 | 6000 | 4.3244 |
| 3.8274 | 4.07 | 6500 | 4.3225 |
| 3.6274 | 4.39 | 7000 | 4.3147 |
| 3.6392 | 4.7 | 7500 | 4.2932 |
| 3.6153 | 5.01 | 8000 | 4.2830 |
| 3.3708 | 5.33 | 8500 | 4.2999 |
| 3.3807 | 5.64 | 9000 | 4.2967 |
| 3.3739 | 5.95 | 9500 | 4.2874 |
| 3.2452 | 6.27 | 10000 | 4.3030 |
| 3.2215 | 6.58 | 10500 | 4.3028 |
| 3.2157 | 6.89 | 11000 | 4.3022 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
digiplay/SDVN1-Real_origin
|
digiplay
| 2023-07-14T07:10:42Z | 38 | 1 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-07-14T05:18:16Z |
---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
https://civitai.com/models/102674?modelVersionId=117203
Sample image I made :
Original Author's DEMO images :
|
nolanaatama/bttrssttchsthprkrvcv2300pchrhys
|
nolanaatama
| 2023-07-14T07:07:24Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-14T07:01:07Z |
---
license: creativeml-openrail-m
---
|
Andyrasika/bloom-560m-lora-tagger
|
Andyrasika
| 2023-07-14T06:59:34Z | 2 | 1 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-14T06:46:01Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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 0.4.0.dev0
```
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
peft_model_id = "Andyrasika/bloom-560m-lora-tagger"
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map='auto')
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
# Load the Lora model
model = PeftModel.from_pretrained(model, peft_model_id)
batch = tokenizer("“Training models with PEFT and LoRa is cool” ->: ", return_tensors='pt')
with torch.cuda.amp.autocast():
output_tokens = model.generate(**batch, max_new_tokens=50)
print('\n\n', tokenizer.decode(output_tokens[0], skip_special_tokens=True))
```
|
Raylei231/QA_for_SO_model
|
Raylei231
| 2023-07-14T06:47:49Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"question-answering",
"generated_from_trainer",
"license:mit",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-07-14T04:01:07Z |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: QA_for_SO_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. -->
# QA_for_SO_model
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0058
## 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: 512
- eval_batch_size: 512
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.0058 | 1.0 | 1037 | 0.0059 |
| 0.0056 | 2.0 | 2074 | 0.0060 |
| 0.0059 | 3.0 | 3111 | 0.0058 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
|
localmodels/WizardLM-7B-v1.0-Uncensored-GPTQ
|
localmodels
| 2023-07-14T06:44:44Z | 6 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-14T06:44:44Z |
---
duplicated_from: localmodels/LLM
---
# WizardLM 7B v1.0 Uncensored GPTQ
From: https://huggingface.co/ehartford/WizardLM-7B-V1.0-Uncensored
---
| Model | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
| wizardlm-7b-v1.0-uncensored-GPTQ-4bit-128g.no-act.order | 4 | 128 | False | 4.00 GB | True | GPTQ-for-LLaMa | Most compatible. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. |
---
# WizardLM 7B v1.0 Uncensored Model Card
This is a retraining of https://huggingface.co/WizardLM/WizardLM-7B-V1.0 with a filtered dataset, intended to reduce refusals, avoidance, and bias.
Note that LLaMA itself has inherent ethical beliefs, so there's no such thing as a "truly uncensored" model. But this model will be more compliant than WizardLM/WizardLM-7B-V1.0.
Shout out to the open source AI/ML community, and everyone who helped me out.
Note: An uncensored model has no guardrails. You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car. Publishing anything this model generates is the same as publishing it yourself. You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.
Unlike WizardLM/WizardLM-7B-V1.0, but like WizardLM/WizardLM-13B-V1.0 and WizardLM/WizardLM-33B-V1.0, this model is trained with Vicuna-1.1 style prompts.
|
ocisd4/openllama_tokenizer_v2
|
ocisd4
| 2023-07-14T06:38:04Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-07-14T03:00:10Z |
```python
from transformers import LlamaTokenizer
tokenizer = LlamaTokenizer.from_pretrained(
'ocisd4/openllama_tokenizer_v2',
add_bos_token=False,
add_eos_token=True,
force_download=False,
use_auth_token=True,
# additional_special_tokens=['<|spcout|>', '<|sep|>', '<|eot|>', '<|output|>']
)
print('vocab size:',tokenizer.vocab_size)
#vocab size: 51456
text = '今天天氣真好！'
print(tokenizer.tokenize(text))
#['▁', '今天', '天氣', '真', '好', '！']
print(tokenizer.encode(text))
#[29500, 32097, 32916, 30615, 30192, 30042, 2]
print(tokenizer.decode(tokenizer.encode(text)))
# 今天天氣真好！</s>
```
|
sd-dreambooth-library/lily
|
sd-dreambooth-library
| 2023-07-14T06:35:40Z | 35 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-07-14T06:34:55Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
---
### Lily on Stable Diffusion via Dreambooth
#### model by rulrul512
This your the Stable Diffusion model fine-tuned the Lily concept taught to Stable Diffusion with Dreambooth.
It can be used by modifying the `instance_prompt`: **painting**
You can also train your own concepts and upload them to the library by using [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb).
And you can run your new concept via `diffusers`: [Colab Notebook for Inference](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_inference.ipynb), [Spaces with the Public Concepts loaded](https://huggingface.co/spaces/sd-dreambooth-library/stable-diffusion-dreambooth-concepts)
Here are the images used for training this concept:
|
edwardjjj/q-FrozenLake-v1-4x4-noSlippery
|
edwardjjj
| 2023-07-14T06:28:20Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-14T06:28:18Z |
---
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="edwardjjj/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"])
```
|
YanJiangJerry/SA-roberta-e12-w1-1.5-b16-augment
|
YanJiangJerry
| 2023-07-14T06:26:35Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"text-classification",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-14T04:37:15Z |
---
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: SA-roberta-e12-w1-1.5-b16-augment
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. -->
# SA-roberta-e12-w1-1.5-b16-augment
This model is a fine-tuned version of [Amalq/autotrain-smm4h_large_roberta_clean-874027878](https://huggingface.co/Amalq/autotrain-smm4h_large_roberta_clean-874027878) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8541
- Accuracy: 0.9188
- F1: 0.8925
- Precision: 0.8808
- Recall: 0.9045
## 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: 12
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.3089 | 1.0 | 581 | 0.4172 | 0.9188 | 0.8889 | 0.9068 | 0.8716 |
| 0.1439 | 2.0 | 1162 | 0.7575 | 0.8910 | 0.8409 | 0.9217 | 0.7731 |
| 0.0988 | 3.0 | 1743 | 0.5909 | 0.9099 | 0.8814 | 0.8649 | 0.8985 |
| 0.0408 | 4.0 | 2324 | 0.6910 | 0.9099 | 0.8831 | 0.8547 | 0.9134 |
| 0.0225 | 5.0 | 2905 | 0.6426 | 0.9188 | 0.8922 | 0.8830 | 0.9015 |
| 0.0196 | 6.0 | 3486 | 0.7218 | 0.9155 | 0.8889 | 0.8711 | 0.9075 |
| 0.0198 | 7.0 | 4067 | 0.7932 | 0.8988 | 0.8691 | 0.8389 | 0.9015 |
| 0.0107 | 8.0 | 4648 | 0.7544 | 0.9155 | 0.8876 | 0.8798 | 0.8955 |
| 0.0036 | 9.0 | 5229 | 0.7316 | 0.9166 | 0.8889 | 0.8824 | 0.8955 |
| 0.0046 | 10.0 | 5810 | 0.8289 | 0.9199 | 0.8932 | 0.8879 | 0.8985 |
| 0.0006 | 11.0 | 6391 | 0.8285 | 0.9188 | 0.8906 | 0.8946 | 0.8866 |
| 0.0027 | 12.0 | 6972 | 0.8541 | 0.9188 | 0.8925 | 0.8808 | 0.9045 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
suarkadipa/HubermanGPT-small-v1
|
suarkadipa
| 2023-07-14T06:21:31Z | 149 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"conversational",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-14T06:20:34Z |
---
pipeline_tag: conversational
---
|
Jonathaniu/vicuna-breast-cancer-7b
|
Jonathaniu
| 2023-07-14T06:20:06Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-14T06:19:53Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
### Framework versions
- PEFT 0.4.0.dev0
|
IIC/BETO_Galen-livingner3
|
IIC
| 2023-07-14T06:16:05Z | 112 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"bert",
"text-classification",
"biomedical",
"clinical",
"spanish",
"BETO_Galen",
"es",
"dataset:IIC/livingner3",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-21T15:32:32Z |
---
language: es
tags:
- biomedical
- clinical
- spanish
- BETO_Galen
license: mit
datasets:
- "IIC/livingner3"
metrics:
- f1
model-index:
- name: IIC/BETO_Galen-livingner3
results:
- task:
type: multi-label-classification
dataset:
name: livingner3
type: IIC/livingner3
split: test
metrics:
- name: f1
type: f1
value: 0.0
pipeline_tag: text-classification
---
# BETO_Galen-livingner3
This model is a finetuned version of BETO_Galen for the livingner3 dataset used in a benchmark in the paper TODO. The model has a F1 of 0.0
Please refer to the original publication for more information TODO LINK
## Parameters used
| parameter | Value |
|-------------------------|:-----:|
| batch size | 64 |
| learning rate | 4e-05 |
| classifier dropout | 0.2 |
| warmup ratio | 0 |
| warmup steps | 0 |
| weight decay | 0 |
| optimizer | AdamW |
| epochs | 10 |
| early stopping patience | 3 |
## BibTeX entry and citation info
```bibtex
TODO
```
|
IIC/bsc-bio-ehr-es-livingner3
|
IIC
| 2023-07-14T06:16:01Z | 109 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"roberta",
"text-classification",
"biomedical",
"clinical",
"spanish",
"bsc-bio-ehr-es",
"es",
"dataset:IIC/livingner3",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-26T07:44:03Z |
---
language: es
tags:
- biomedical
- clinical
- spanish
- bsc-bio-ehr-es
license: apache-2.0
datasets:
- "IIC/livingner3"
metrics:
- f1
model-index:
- name: IIC/bsc-bio-ehr-es-livingner3
results:
- task:
type: multi-label-classification
dataset:
name: livingner3
type: IIC/livingner3
split: test
metrics:
- name: f1
type: f1
value: 0.604
pipeline_tag: text-classification
---
# bsc-bio-ehr-es-livingner3
This model is a finetuned version of bsc-bio-ehr-es for the livingner3 dataset used in a benchmark in the paper TODO. The model has a F1 of 0.604
Please refer to the original publication for more information TODO LINK
## Parameters used
| parameter | Value |
|-------------------------|:-----:|
| batch size | 16 |
| learning rate | 3e-05 |
| classifier dropout | 0.1 |
| warmup ratio | 0 |
| warmup steps | 0 |
| weight decay | 0 |
| optimizer | AdamW |
| epochs | 10 |
| early stopping patience | 3 |
## BibTeX entry and citation info
```bibtex
TODO
```
|
IIC/bsc-bio-ehr-es-meddocan
|
IIC
| 2023-07-14T06:15:56Z | 106 | 1 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"roberta",
"text-classification",
"biomedical",
"clinical",
"spanish",
"bsc-bio-ehr-es",
"token-classification",
"es",
"dataset:bigbio/meddocan",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-06-21T15:43:34Z |
---
language: es
tags:
- biomedical
- clinical
- spanish
- bsc-bio-ehr-es
license: apache-2.0
datasets:
- "bigbio/meddocan"
metrics:
- f1
model-index:
- name: IIC/bsc-bio-ehr-es-meddocan
results:
- task:
type: token-classification
dataset:
name: meddocan
type: bigbio/meddocan
split: test
metrics:
- name: f1
type: f1
value: 0.967
pipeline_tag: token-classification
---
# bsc-bio-ehr-es-meddocan
This model is a finetuned version of bsc-bio-ehr-es for the meddocan dataset used in a benchmark in the paper TODO. The model has a F1 of 0.967
Please refer to the original publication for more information TODO LINK
## Parameters used
| parameter | Value |
|-------------------------|:-----:|
| batch size | 16 |
| learning rate | 4e-05 |
| classifier dropout | 0 |
| warmup ratio | 0 |
| warmup steps | 0 |
| weight decay | 0 |
| optimizer | AdamW |
| epochs | 10 |
| early stopping patience | 3 |
## BibTeX entry and citation info
```bibtex
TODO
```
|
au2a/whisper-medium-zh-20230712
|
au2a
| 2023-07-14T06:01:08Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"zh",
"dataset:-",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-07-12T13:10:31Z |
---
language:
- zh
license: apache-2.0
tags:
- whisper
- generated_from_trainer
datasets:
- '-'
model-index:
- name: whisper-medium-zh-20230712 - au2a
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. -->
# whisper-medium-zh-20230712 - au2a
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the some hakka audio dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2659
- Cer: 87.6898
## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 15000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
| 0.2417 | 0.16 | 1000 | 0.3919 | 92.1659 |
| 0.1219 | 0.32 | 2000 | 0.2963 | 81.3855 |
| 0.0762 | 0.49 | 3000 | 0.2785 | 68.9544 |
| 0.0524 | 0.65 | 4000 | 0.2660 | 89.4916 |
| 0.0347 | 0.81 | 5000 | 0.2517 | 96.8800 |
| 0.0255 | 0.97 | 6000 | 0.2567 | 89.0232 |
| 0.0104 | 1.13 | 7000 | 0.2547 | 91.9959 |
| 0.0069 | 1.29 | 8000 | 0.2609 | 85.5481 |
| 0.0072 | 1.46 | 9000 | 0.2605 | 72.8148 |
| 0.0081 | 1.62 | 10000 | 0.2593 | 81.8161 |
| 0.0024 | 1.78 | 11000 | 0.2608 | 79.6064 |
| 0.0021 | 1.94 | 12000 | 0.2622 | 78.2655 |
| 0.0004 | 2.1 | 13000 | 0.2656 | 86.0580 |
| 0.0005 | 2.27 | 14000 | 0.2665 | 90.1677 |
| 0.0005 | 2.43 | 15000 | 0.2659 | 87.6898 |
### Framework versions
- Transformers 4.30.2
- Pytorch 1.11.0+cu113
- Datasets 2.13.1
- Tokenizers 0.13.3
|
localmodels/Airoboros-33B-gpt4-1.4-GPTQ
|
localmodels
| 2023-07-14T05:55:28Z | 5 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-14T05:55:28Z |
---
duplicated_from: localmodels/LLM
---
# Airoboros 33B GPT4 1.4 GPTQ
From: https://huggingface.co/jondurbin/airoboros-33B-gpt4-1.4
---
| Model | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
| main | 4 | None | True | 16.94 GB | True | GPTQ-for-LLaMa | Most compatible. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. |
---
# Model Card: Airoboros 33B GPT4 1.4
## Overview
This is a qlora fine-tune 33b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
This is mostly an extension of the previous gpt-4 series, with a few extras:
* fixed (+ more examples of) multi-character, multi-turn conversations
* coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
* more roleplay examples
* jokes
* riddles
* all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)
This model was fine-tuned with a fork of [qlora](https://github.com/jondurbin/qlora)
The prompt it was trained with was:
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
## Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-33b-gpt4-1.4 \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
For multi-turn conversations and chatting, you'll want to remove the `--no-history` option.
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a newline and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js.
PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMA, which has its own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially.
|
mihirtw/med-app-falcon-7b
|
mihirtw
| 2023-07-14T05:54:33Z | 0 | 0 | null |
[
"tensorboard",
"generated_from_trainer",
"region:us"
] | null | 2023-07-14T04:43:37Z |
---
tags:
- generated_from_trainer
model-index:
- name: results
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. -->
# results
This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) 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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 50
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
NasimB/gpt2-concat-simple-wiki-mod-rarity-all-no-cut
|
NasimB
| 2023-07-14T05:45:45Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:generator",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-14T03:52:18Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-concat-simple-wiki-mod-rarity-all-no-cut
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. -->
# gpt2-concat-simple-wiki-mod-rarity-all-no-cut
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 4.3462
## 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: 0.0005
- 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: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.6774 | 0.29 | 500 | 5.6364 |
| 5.3296 | 0.59 | 1000 | 5.2066 |
| 4.9846 | 0.88 | 1500 | 4.9630 |
| 4.7143 | 1.17 | 2000 | 4.8166 |
| 4.5671 | 1.47 | 2500 | 4.6964 |
| 4.4602 | 1.76 | 3000 | 4.6054 |
| 4.3491 | 2.06 | 3500 | 4.5378 |
| 4.1571 | 2.35 | 4000 | 4.4850 |
| 4.1355 | 2.64 | 4500 | 4.4260 |
| 4.0891 | 2.94 | 5000 | 4.3742 |
| 3.8782 | 3.23 | 5500 | 4.3681 |
| 3.8308 | 3.52 | 6000 | 4.3389 |
| 3.8143 | 3.82 | 6500 | 4.2994 |
| 3.6943 | 4.11 | 7000 | 4.3005 |
| 3.5497 | 4.4 | 7500 | 4.2925 |
| 3.5336 | 4.7 | 8000 | 4.2784 |
| 3.5253 | 4.99 | 8500 | 4.2637 |
| 3.357 | 5.28 | 9000 | 4.2795 |
| 3.3454 | 5.58 | 9500 | 4.2779 |
| 3.3495 | 5.87 | 10000 | 4.2771 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
localmodels/Nous-Hermes-13B-GPTQ
|
localmodels
| 2023-07-14T05:28:54Z | 5 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-14T05:28:53Z |
---
duplicated_from: localmodels/LLM
---
# Nous-Hermes-13B GPTQ
From: https://huggingface.co/NousResearch/Nous-Hermes-13b
---
## Model
* nous-hermes-13b-GPTQ-4bit-128g.no-act.order.safetensors
* Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
* Works with AutoGPTQ
* Parameters: Groupsize = 128. No act-order.
---
# Model Card: Nous-Hermes-13b
## Model Description
Nous-Hermes-13b is a state-of-the-art language model fine-tuned on over 300,000 instructions. This model was fine-tuned by Nous Research, with Teknium and Karan4D leading the fine tuning process and dataset curation, Redmond AI sponsoring the compute, and several other contributors. The result is an enhanced Llama 13b model that rivals GPT-3.5-turbo in performance across a variety of tasks.
This model stands out for its long responses, low hallucination rate, and absence of OpenAI censorship mechanisms. The fine-tuning process was performed with a 2000 sequence length on an 8x a100 80GB DGX machine for over 50 hours.
## Model Training
The model was trained almost entirely on synthetic GPT-4 outputs. This includes data from diverse sources such as GPTeacher, the general, roleplay v1&2, code instruct datasets, Nous Instruct & PDACTL (unpublished), CodeAlpaca, Evol_Instruct Uncensored, GPT4-LLM, and Unnatural Instructions.
Additional data inputs came from Camel-AI's Biology/Physics/Chemistry and Math Datasets, Airoboros' GPT-4 Dataset, and more from CodeAlpaca. The total volume of data encompassed over 300,000 instructions.
## Collaborators
The model fine-tuning and the datasets were a collaboration of efforts and resources between Teknium, Karan4D, Nous Research, Huemin Art, and Redmond AI.
Huge shoutout and acknowledgement is deserved for all the dataset creators who generously share their datasets openly.
Special mention goes to @winglian, @erhartford, and @main_horse for assisting in some of the training issues.
Among the contributors of datasets, GPTeacher was made available by Teknium, Wizard LM by nlpxucan, and the Nous Research Instruct Dataset was provided by Karan4D and HueminArt.
The GPT4-LLM and Unnatural Instructions were provided by Microsoft, Airoboros dataset by jondurbin, Camel-AI datasets are from Camel-AI, and CodeAlpaca dataset by Sahil 2801.
If anyone was left out, please open a thread in the community tab.
## Prompt Format
The model follows the Alpaca prompt format:
```
### Instruction:
### Response:
```
or
```
### Instruction:
### Input:
### Response:
```
|
localmodels/Nous-Hermes-13B-ggml
|
localmodels
| 2023-07-14T05:26:41Z | 0 | 2 | null |
[
"region:us"
] | null | 2023-07-14T05:26:41Z |
---
duplicated_from: localmodels/LLM
---
# Nous-Hermes-13B ggml
From: https://huggingface.co/NousResearch/Nous-Hermes-13b
---
### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
Quantized using an older version of llama.cpp and compatible with llama.cpp from May 19, commit 2d5db48.
### k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
Quantization methods compatible with latest llama.cpp from June 6, commit 2d43387.
---
## Provided Files
| Name | Quant method | Bits | Size | Max RAM required, no GPU offloading | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| nous-hermes-13b.ggmlv3.q2_K.bin | q2_K | 2 | 5.43 GB | 7.93 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| nous-hermes-13b.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 6.87 GB | 9.37 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| nous-hermes-13b.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.25 GB | 8.75 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| nous-hermes-13b.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.59 GB | 8.09 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| nous-hermes-13b.ggmlv3.q4_0.bin | q4_0 | 4 | 7.32 GB | 9.82 GB | Original llama.cpp quant method, 4-bit. |
| nous-hermes-13b.ggmlv3.q4_1.bin | q4_1 | 4 | 8.14 GB | 10.64 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| nous-hermes-13b.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.82 GB | 10.32 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| nous-hermes-13b.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.32 GB | 9.82 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| nous-hermes-13b.ggmlv3.q5_0.bin | q5_0 | 5 | 8.95 GB | 11.45 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| nous-hermes-13b.ggmlv3.q5_1.bin | q5_1 | 5 | 9.76 GB | 12.26 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| nous-hermes-13b.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.21 GB | 11.71 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| nous-hermes-13b.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 8.95 GB | 11.45 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| nous-hermes-13b.ggmlv3.q6_K.bin | q6_K | 6 | 10.68 GB | 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| nous-hermes-13b.ggmlv3.q8_0.bin | q8_0 | 8 | 13.83 GB | 16.33 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
---
# Model Card: Nous-Hermes-13b
## Model Description
Nous-Hermes-13b is a state-of-the-art language model fine-tuned on over 300,000 instructions. This model was fine-tuned by Nous Research, with Teknium and Karan4D leading the fine tuning process and dataset curation, Redmond AI sponsoring the compute, and several other contributors. The result is an enhanced Llama 13b model that rivals GPT-3.5-turbo in performance across a variety of tasks.
This model stands out for its long responses, low hallucination rate, and absence of OpenAI censorship mechanisms. The fine-tuning process was performed with a 2000 sequence length on an 8x a100 80GB DGX machine for over 50 hours.
## Model Training
The model was trained almost entirely on synthetic GPT-4 outputs. This includes data from diverse sources such as GPTeacher, the general, roleplay v1&2, code instruct datasets, Nous Instruct & PDACTL (unpublished), CodeAlpaca, Evol_Instruct Uncensored, GPT4-LLM, and Unnatural Instructions.
Additional data inputs came from Camel-AI's Biology/Physics/Chemistry and Math Datasets, Airoboros' GPT-4 Dataset, and more from CodeAlpaca. The total volume of data encompassed over 300,000 instructions.
## Collaborators
The model fine-tuning and the datasets were a collaboration of efforts and resources between Teknium, Karan4D, Nous Research, Huemin Art, and Redmond AI.
Huge shoutout and acknowledgement is deserved for all the dataset creators who generously share their datasets openly.
Special mention goes to @winglian, @erhartford, and @main_horse for assisting in some of the training issues.
Among the contributors of datasets, GPTeacher was made available by Teknium, Wizard LM by nlpxucan, and the Nous Research Instruct Dataset was provided by Karan4D and HueminArt.
The GPT4-LLM and Unnatural Instructions were provided by Microsoft, Airoboros dataset by jondurbin, Camel-AI datasets are from Camel-AI, and CodeAlpaca dataset by Sahil 2801.
If anyone was left out, please open a thread in the community tab.
## Prompt Format
The model follows the Alpaca prompt format:
```
### Instruction:
### Response:
```
or
```
### Instruction:
### Input:
### Response:
```
## Benchmark Results
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.4915|± |0.0146|
| | |acc_norm|0.5085|± |0.0146|
|arc_easy | 0|acc |0.7769|± |0.0085|
| | |acc_norm|0.7424|± |0.0090|
|boolq | 1|acc |0.7948|± |0.0071|
|hellaswag | 0|acc |0.6143|± |0.0049|
| | |acc_norm|0.8000|± |0.0040|
|openbookqa | 0|acc |0.3560|± |0.0214|
| | |acc_norm|0.4640|± |0.0223|
|piqa | 0|acc |0.7965|± |0.0094|
| | |acc_norm|0.7889|± |0.0095|
|winogrande | 0|acc |0.7190|± |0.0126|
```
|
Craap/image-generation
|
Craap
| 2023-07-14T05:25:37Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-07-06T02:57:26Z |
These are pretrained weights for my stuff at https://github.com/Craap/models
|
enlightenai/real_vision
|
enlightenai
| 2023-07-14T05:24:09Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-14T05:23:31Z |
---
license: creativeml-openrail-m
---
<b>The recommended negative prompt:</b><br>
(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck<br>
<b>OR</b><br>
(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation
<b>Recommended parameters for generation:</b><br>
Euler A or DPM++ SDE Karras<br>
CFG Scale 3,5 - 15<br>
Hires. fix with 4x-UltraSharp upscaler<br>
0 Hires steps and Denoising strength 0.25-0.7<br>
Upscale by 1.1-2.0
|
localmodels/Pygmalion-13B-GPTQ
|
localmodels
| 2023-07-14T05:15:32Z | 5 | 1 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-14T05:15:32Z |
---
duplicated_from: localmodels/LLM
---
# Pygmalion 13B GPTQ
From PygmalionAI: https://huggingface.co/PygmalionAI/pygmalion-13b
---
## Model Details
Pygmalion 13B is a dialogue model based on Meta's LLaMA-13B.
This is version 1. It has been fine-tuned using a subset of the data from Pygmalion-6B-v8-pt4, for those of you familiar with the project.
## Prompting
The model was trained on the usual Pygmalion persona + chat format, so any of the usual UIs should already handle everything correctly. If you're using the model directly, this is the expected formatting:
```
[CHARACTER]'s Persona: [A few sentences about the character you want the model to play]
<START>
[DIALOGUE HISTORY]
You: [User's input message here]
[CHARACTER]:
```
Where `[CHARACTER]` is, as you can probably guess, the name of the character you want the model to portray, `<START>` should be used verbatim as a delimiter token to separate persona and scenario data from the dialogue, and `[DIALOGUE HISTORY]` is a sliding window of chat history so the model can have conversational context to draw from. Here's a concrete example:
```
Assistant's Persona: Assistant is a highly intelligent language model trained to comply with user requests.
<START>
Assistant: Hello! How may I help you today?
You: What is Zork?
Assistant:
```
Which will generate something like:
```
Zork is an interactive fiction computer game created in the 1970s by Infocom, Inc., which was later acquired by Activision Blizzard. It is widely considered one of the most influential games ever made and has been credited with popularizing text-based adventure games. The original version of Zork was written in the programming language MACRO-10, but it was ported to many other platforms over the years."
```
The model will automatically emit an end-of-text token (`</s>`) when it judges that the response is complete.
## Other notes
- The model was trained as a LoRA with a somewhat unorthodox configuration which causes errors when used with the current version of `peft`, hence we release it as a full model instead.
## Limitations and biases
The intended use-case for this model is fictional conversation for entertainment purposes. Any other sort of usage is out of scope.
As such, it was **not** fine-tuned to be safe and harmless: the base model _and_ this fine-tune have been trained on data known to contain profanity and texts that are lewd or otherwise offensive. It may produce socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. Outputs might often be factually wrong or misleading.
|
foxxy-hm/e2eqa-wiki
|
foxxy-hm
| 2023-07-14T05:04:25Z | 0 | 0 |
generic
|
[
"generic",
"question-answering",
"optimum",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-07-05T05:26:59Z |
---
tags:
- question-answering
- optimum
library_name: generic
---
|
NasimB/gpt2-concat-simple-wiki-rarity-all-no-cut
|
NasimB
| 2023-07-14T04:54:24Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:generator",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-07-14T02:59:33Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-concat-simple-wiki-rarity-all-no-cut
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. -->
# gpt2-concat-simple-wiki-rarity-all-no-cut
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 4.3535
## 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: 0.0005
- 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: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.7004 | 0.29 | 500 | 5.6313 |
| 5.335 | 0.58 | 1000 | 5.1992 |
| 4.9864 | 0.87 | 1500 | 4.9605 |
| 4.7328 | 1.17 | 2000 | 4.8244 |
| 4.578 | 1.46 | 2500 | 4.7056 |
| 4.4753 | 1.75 | 3000 | 4.6075 |
| 4.3596 | 2.04 | 3500 | 4.5420 |
| 4.1677 | 2.33 | 4000 | 4.4944 |
| 4.1371 | 2.62 | 4500 | 4.4336 |
| 4.0946 | 2.91 | 5000 | 4.3802 |
| 3.8963 | 3.21 | 5500 | 4.3779 |
| 3.8338 | 3.5 | 6000 | 4.3423 |
| 3.821 | 3.79 | 6500 | 4.3127 |
| 3.7341 | 4.08 | 7000 | 4.3030 |
| 3.5486 | 4.37 | 7500 | 4.3027 |
| 3.5395 | 4.66 | 8000 | 4.2869 |
| 3.528 | 4.95 | 8500 | 4.2755 |
| 3.3801 | 5.24 | 9000 | 4.2873 |
| 3.3538 | 5.54 | 9500 | 4.2853 |
| 3.3452 | 5.83 | 10000 | 4.2848 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
nbroad/setfit-sci-wiki
|
nbroad
| 2023-07-14T04:30:37Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-07-14T04:30:12Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# nbroad/setfit-sci-wiki
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("nbroad/setfit-sci-wiki")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
matgu23/cntblv
|
matgu23
| 2023-07-14T04:27:14Z | 2 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-07-14T04:23:23Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### cntblv Dreambooth model trained by matgu23 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
Sumayan/Sumayan
|
Sumayan
| 2023-07-14T04:11:08Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-14T04:11:08Z |
---
license: creativeml-openrail-m
---
|
Chickenfish/Dayteurbr
|
Chickenfish
| 2023-07-14T04:08:09Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-07-14T04:07:29Z |
---
license: creativeml-openrail-m
---
|
BrendaScar/Taxi-v3-Qtable
|
BrendaScar
| 2023-07-14T04:03:52Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-14T04:03:50Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3-Qtable
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="BrendaScar/Taxi-v3-Qtable", 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"])
```
|
fnlp/moss-rlhf-sft-model-7B-en
|
fnlp
| 2023-07-14T03:28:15Z | 0 | 2 | null |
[
"llm",
"moss",
"rlhf",
"sft",
"zh",
"arxiv:2307.04964",
"license:agpl-3.0",
"region:us"
] | null | 2023-07-13T08:03:11Z |
---
license: agpl-3.0
language:
- zh
tags:
- llm
- moss
- rlhf
- sft
---
# MOSS-RLHF
### *MOSS-RLHF & "Secrets of RLHF in Large Language Models Part I: PPO" <br>👉 <a href="https://arxiv.org/abs/2307.04964" target="_blank">[Technical report]</a> <a href="https://openlmlab.github.io/MOSS-RLHF/" target="_blank">[Home page]*
## 🌟 News
### 👉 Wed, 12. July 2023. We have released Chinese reward model based OpenChineseLlama-7B!
[moss-rlhf-reward-model-7B-zh](https://huggingface.co/Ablustrund/moss-rlhf-reward-model-7B-zh/tree/main)
<br>
### 👉 Thu, 13. July 2023. We have released English reward model and SFT model based Llama-7B!
[moss-rlhf-reward-model-7B-en](https://huggingface.co/fnlp/moss-rlhf-reward-model-7B-en)
[moss-rlhf-sft-model-7B-en](https://huggingface.co/fnlp/moss-rlhf-sft-model-7B-en)
<br>
## 🧾 Open-source List
- [x] Open source code for RL training in large language models.
- [x] A 7B Chinese reward model based on openChineseLlama.
- [x] A 7B English reward model based on Llama-7B.
- [x] SFT model for English.
- [ ] Policy model for English after RLHF.
- ...
## 🌠 Introduction
Due to the challenges of reward design, environment interaction, and agent training, coupled with huge trial and error cost of large language models, there is a significant barrier for AI researchers to motivate the development of technical alignment and safe landing of LLMs. The stable training of RLHF has still been a puzzle.
In this technical report, we intend to help researchers to train their models stably with human feedback.
Contributions are summarized as follows:
1) We release competitive Chinese and English reward models, respectively, which have good cross-model generalization ability, alleviating the cost of relabeling human preference data;
2) We conduct in-depth analysis on the inner workings of PPO algorithm and propose the PPO-max algorithm to ensure stable model training;
3) We release the complete PPO-max codes to ensure that the LLMs in the current SFT stage can be better aligned with humans.
## 🔩 Requirements & Setup
This repository works on Python 3.8 and PyTorch 1.13.1.
We recommend using the **conda** virtual environment to run the code.
#### Step 1: Create a new Python virtual environment
```bash
conda update conda -n base -c defaults
conda create -n rlhf python=3.8
conda activate rlhf
```
#### Step 2: Install PyTorch and TensorBoard
```bash
conda install pytorch==1.13.1 pytorch-cuda=11.7 tensorboard -c pytorch -c nvidia
```
#### Step 3: Install the remaining dependencies
```bash
conda install datasets accelerate safetensors chardet cchardet -c huggingface -c conda-forge
pip3 install transformers sentencepiece einops triton==1.0.0 rouge jionlp==1.4.14 nltk sacrebleu cpm_kernels
apt install libaio-dev
DS_BUILD_OPS=1 pip install deepspeed
```
## ✨ Start training your own model!
Run code in a few steps.
### Step 1: Recover Reward model weights
We can not directly release the full weight of the reward model because of protocol restrictions.
You can merge the diff weight with original Llama-7B to recover the reward model we used.
We upload the diff models, thanks to tatsu-lab, you can recover the reward model follow these steps:
```bash
1) Download the weight diff into your local machine. The weight diff is located at:
# For English:
TODO
# For Chinese:
https://huggingface.co/Ablustrund/moss-rlhf-reward-model-7B-zh/tree/main
2) Merge the weight diff with the original Llama-7B:
# For English:
# Reward model
python merge_weight_en.py recover --path_raw decapoda-research/llama-7b-hf --path_diff ./models/moss-rlhf-reward-model-7B-en/diff --path_tuned ./models/moss-rlhf-reward-model-7B-en/recover --model_type reward
# SFT model
python merge_weight_en.py recover --path_raw decapoda-research/llama-7b-hf --path_diff ./models/moss-rlhf-sft-model-7B-en/diff --path_tuned ./models/moss-rlhf-sft-model-7B-en/recover --model_type sft
# Policy model
TODO
# For Chinese:
python merge_weight_zh.py recover --path_raw decapoda-research/llama-7b-hf --path_diff ./models/moss-rlhf-reward-model-7B-zh/diff --path_tuned ./models/moss-rlhf-reward-model-7B-zh/recover
```
### Step 2: Select your own SFT model.
Because of some limitations, we can not release the **Chinese** SFT model (Currently).
You can use your own SFT model, or a strong base model instead of our SFT model.
### Step 3: Start training
Run the command below.
```
# For Chinese:
# You need to use your own sft model currently.
bash run_zh.sh
# For English:
# We have loaded the sft model and reward model to huggingface.
bash run_en.sh
```
## Citation
```bibtex
@article{zheng2023secrets,
title={Secrets of RLHF in Large Language Models Part I: PPO},
author={Rui Zheng and Shihan Dou and Songyang Gao and Wei Shen and Binghai Wang and Yan Liu and Senjie Jin and Qin Liu and Limao Xiong and Lu Chen and Zhiheng Xi and Yuhao Zhou and Nuo Xu and Wenbin Lai and Minghao Zhu and Rongxiang Weng and Wensen Cheng and Cheng Chang and Zhangyue Yin and Yuan Hua and Haoran Huang and Tianxiang Sun and Hang Yan and Tao Gui and Qi Zhang and Xipeng Qiu and Xuanjing Huang},
year={2023},
eprint={2307.04964},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
11old/11
|
11old
| 2023-07-14T03:16:29Z | 0 | 0 | null |
[
"license:bigscience-bloom-rail-1.0",
"region:us"
] | null | 2023-07-14T03:16:29Z |
---
license: bigscience-bloom-rail-1.0
---
|
justairr/BetterPrompt
|
justairr
| 2023-07-14T03:11:36Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-07-13T12:37:51Z |
---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
A Prompt Generator and Enhancer based on ChatGLM
|
junejae/distilbert-base-uncased-finetuned-emotion
|
junejae
| 2023-07-14T02:57:50Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-14T02:02:49Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.918
- name: F1
type: f1
value: 0.9183451843024099
---
<!-- 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-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2300
- Accuracy: 0.918
- F1: 0.9183
## 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: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8386 | 1.0 | 250 | 0.3276 | 0.904 | 0.9011 |
| 0.2572 | 2.0 | 500 | 0.2300 | 0.918 | 0.9183 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
bh8648/xlm-roberta-base-finetuned-panx-de
|
bh8648
| 2023-07-14T02:47:54Z | 135 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-07-14T00:23:23Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-de
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.de
split: validation
args: PAN-X.de
metrics:
- name: F1
type: f1
value: 0.8606226168117922
---
<!-- 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. -->
# xlm-roberta-base-finetuned-panx-de
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1533
- F1: 0.8606
## 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: 10
- eval_batch_size: 10
- 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2527 | 1.0 | 1258 | 0.1823 | 0.8204 |
| 0.1358 | 2.0 | 2516 | 0.1534 | 0.8410 |
| 0.081 | 3.0 | 3774 | 0.1533 | 0.8606 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
sumandeng/my-m3e-base
|
sumandeng
| 2023-07-14T02:29:36Z | 15 | 1 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"safetensors",
"bert",
"embedding",
"text-embedding",
"zh",
"en",
"region:us"
] | null | 2023-08-02T13:27:13Z |
---
language:
- zh
- en
tags:
- embedding
- text-embedding
library_name: sentence-transformers
---
# 🅜 M3E Models
[m3e-small](https://huggingface.co/moka-ai/m3e-small) | [m3e-base](https://huggingface.co/moka-ai/m3e-base)
M3E 是 Moka Massive Mixed Embedding 的缩写
- Moka，此模型由 MokaAI 训练，开源和评测，训练脚本使用 [uniem](https://github.com/wangyuxinwhy/uniem/blob/main/scripts/train_m3e.py) ，评测 BenchMark 使用 [MTEB-zh](https://github.com/wangyuxinwhy/uniem/tree/main/mteb-zh)
- Massive，此模型通过**千万级** (2200w+) 的中文句对数据集进行训练
- Mixed，此模型支持中英双语的同质文本相似度计算，异质文本检索等功能，未来还会支持代码检索
- Embedding，此模型是文本嵌入模型，可以将自然语言转换成稠密的向量
## 🆕 更新说明
- 2023.06.24，添加微调 M3E 的教程 [notebook](https://github.com/wangyuxinwhy/uniem/blob/main/examples/finetune.ipynb)，几行代码，更佳适配！<a target="_blank" href="https://colab.research.google.com/github/wangyuxinwhy/uniem/blob/main/examples/finetune.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
- 2023.06.14，添加了三个中文开源文本嵌入模型到评测中，包括 UER, ErLangShen, DMetaSoul
- 2023.06.08，添加检索任务的评测结果，在 T2Ranking 1W 中文数据集上，m3e-base 在 ndcg@10 上达到了 0.8004，超过了 openai-ada-002 的 0.7786
- 2023.06.07，添加文本分类任务的评测结果，在 6 种文本分类数据集上，m3e-base 在 accuracy 上达到了 0.6157，超过了 openai-ada-002 的 0.5956
## ⚖️ 模型对比
| | 参数数量 | 维度 | 中文 | 英文 | s2s | s2p | s2c | 开源 | 兼容性 | s2s Acc | s2p ndcg@10 |
| --------- | -------- | -------- | -------- | -------- | -------- | -------- | -------- | ---- | ---------- | ------------ | -------- |
| m3e-small | 24M | 512 | 是 | 否 | 是 | 否 | 否 | 是 | 优 | 0.5834 | 0.7262 |
| m3e-base | 110M | 768 | 是 | 是 | 是 | 是 | 否 | 是 | 优 | **0.6157** | **0.8004** |
| text2vec | 110M | 768 | 是 | 否 | 是 | 否 | 否 | 是 | 优 | 0.5755 | 0.6346 |
| openai-ada-002 | 未知 | 1536 | 是 | 是 | 是 | 是 | 是 | 否 | 优 | 0.5956 | 0.7786 |
说明：
- s2s, 即 sentence to sentence ，代表了同质文本之间的嵌入能力，适用任务：文本相似度，重复问题检测，文本分类等
- s2p, 即 sentence to passage ，代表了异质文本之间的嵌入能力，适用任务：文本检索，GPT 记忆模块等
- s2c, 即 sentence to code ，代表了自然语言和程序语言之间的嵌入能力，适用任务：代码检索
- 兼容性，代表了模型在开源社区中各种项目被支持的程度，由于 m3e 和 text2vec 都可以直接通过 sentence-transformers 直接使用，所以和 openai 在社区的支持度上相当
- ACC & ndcg@10，详情见下方的评测
Tips:
- 使用场景主要是中文，少量英文的情况，建议使用 m3e 系列的模型
- 多语言使用场景，并且不介意数据隐私的话，我建议使用 openai text-embedding-ada-002
- 代码检索场景，推荐使用 openai text-embedding-ada-002
- 文本检索场景，请使用具备文本检索能力的模型，只在 S2S 上训练的文本嵌入模型，没有办法完成文本检索任务
## 🔧 使用 M3E
您需要先安装 sentence-transformers
```bash
pip install -U sentence-transformers
```
安装完成后，您可以使用以下代码来使用 M3E Models
```python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('moka-ai/m3e-base')
#Our sentences we like to encode
sentences = [
'* Moka 此文本嵌入模型由 MokaAI 训练并开源，训练脚本使用 uniem',
'* Massive 此文本嵌入模型通过**千万级**的中文句对数据集进行训练',
'* Mixed 此文本嵌入模型支持中英双语的同质文本相似度计算，异质文本检索等功能，未来还会支持代码检索，ALL in one'
]
#Sentences are encoded by calling model.encode()
embeddings = model.encode(sentences)
#Print the embeddings
for sentence, embedding in zip(sentences, embeddings):
print("Sentence:", sentence)
print("Embedding:", embedding)
print("")
```
M3E 系列的所有模型在设计的时候就考虑到完全兼容 [sentence-transformers](https://www.sbert.net/) ，所以你可以通过**替换名称字符串**的方式在所有支持 sentence-transformers 的项目中**无缝**使用 M3E Models，比如 [chroma](https://docs.trychroma.com/getting-started), [guidance](https://github.com/microsoft/guidance), [semantic-kernel](https://github.com/microsoft/semantic-kernel) 。
## 🎨 微调模型
`uniem` 提供了非常易用的 finetune 接口，几行代码，即刻适配！
```python
from datasets import load_dataset
from uniem.finetuner import FineTuner
dataset = load_dataset('shibing624/nli_zh', 'STS-B')
# 指定训练的模型为 m3e-small
finetuner = FineTuner.from_pretrained('moka-ai/m3e-small', dataset=dataset)
finetuner.run(epochs=1)
```
详见 [uniem 微调教程](https://github.com/wangyuxinwhy/uniem/blob/main/examples/finetune.ipynb)
<a target="_blank" href="https://colab.research.google.com/github/wangyuxinwhy/uniem/blob/main/examples/finetune.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
## ➿ 训练方案
M3E 使用 in-batch 负采样的对比学习的方式在句对数据集进行训练，为了保证 in-batch 负采样的效果，我们使用 A100 80G 来最大化 batch-size，并在共计 2200W+ 的句对数据集上训练了 1 epoch。训练脚本使用 [uniem](https://github.com/wangyuxinwhy/uniem/blob/main/scripts/train_m3e.py)，您可以在这里查看具体细节。
## 🌟 特性
- 中文训练集，M3E 在大规模句对数据集上的训练，包含中文百科，金融，医疗，法律，新闻，学术等多个领域共计 2200W 句对样本，数据集详见 [M3E 数据集](#M3E数据集)
- 英文训练集，M3E 使用 MEDI 145W 英文三元组数据集进行训练，数据集详见 [MEDI 数据集](https://drive.google.com/file/d/1vZ5c2oJNonGOvXzppNg5mHz24O6jcc52/view)，此数据集由 [instructor team](https://github.com/HKUNLP/instructor-embedding) 提供
- 指令数据集，M3E 使用了 300W + 的指令微调数据集，这使得 M3E 对文本编码的时候可以遵从指令，这部分的工作主要被启发于 [instructor-embedding](https://github.com/HKUNLP/instructor-embedding)
- 基础模型，M3E 使用 hfl 实验室的 [Roberta](https://huggingface.co/hfl/chinese-roberta-wwm-ext) 系列模型进行训练，目前提供 small 和 base 两个版本，大家则需选用
- ALL IN ONE，M3E 旨在提供一个 ALL IN ONE 的文本嵌入模型，不仅支持同质句子相似度判断，还支持异质文本检索，你只需要一个模型就可以覆盖全部的应用场景，未来还会支持代码检索
## 💯 MTEB-zh 评测
- 评测模型，[text2vec](https://github.com/shibing624/text2vec), m3e-base, m3e-small, openai text-embedding-ada-002, [DMetaSoul](https://huggingface.co/DMetaSoul/sbert-chinese-general-v2), [UER](https://huggingface.co/uer/sbert-base-chinese-nli), [ErLangShen](https://huggingface.co/IDEA-CCNL/Erlangshen-SimCSE-110M-Chinese)
- 评测脚本，具体参考 [MTEB-zh] (https://github.com/wangyuxinwhy/uniem/blob/main/mteb-zh)
### 文本分类
- 数据集选择，选择开源在 HuggingFace 上的 6 种文本分类数据集，包括新闻、电商评论、股票评论、长文本等
- 评测方式，使用 MTEB 的方式进行评测，报告 Accuracy。
| | text2vec | m3e-small | m3e-base | openai | DMetaSoul | uer | erlangshen |
| ----------------- | -------- | --------- | -------- | ------ | ----------- | ------- | ----------- |
| TNews | 0.43 | 0.4443 | **0.4827** | 0.4594 | 0.3084 | 0.3539 | 0.4361 |
| JDIphone | 0.8214 | 0.8293 | **0.8533** | 0.746 | 0.7972 | 0.8283 | 0.8356 |
| GubaEastmony | 0.7472 | 0.712 | 0.7621 | 0.7574 | 0.735 | 0.7534 | **0.7787** |
| TYQSentiment | 0.6099 | 0.6596 | **0.7188** | 0.68 | 0.6437 | 0.6662 | 0.6444 |
| StockComSentiment | 0.4307 | 0.4291 | 0.4363 | **0.4819** | 0.4309 | 0.4555 | 0.4482 |
| IFlyTek | 0.414 | 0.4263 | 0.4409 | **0.4486** | 0.3969 | 0.3762 | 0.4241 |
| Average | 0.5755 | 0.5834 | **0.6157** | 0.5956 | 0.552016667 | 0.57225 | 0.594516667 |
### 检索排序
#### T2Ranking 1W
- 数据集选择，使用 [T2Ranking](https://github.com/THUIR/T2Ranking/tree/main) 数据集，由于 T2Ranking 的数据集太大，openai 评测起来的时间成本和 api 费用有些高，所以我们只选择了 T2Ranking 中的前 10000 篇文章
- 评测方式，使用 MTEB 的方式进行评测，报告 map@1, map@10, mrr@1, mrr@10, ndcg@1, ndcg@10
- 注意！从实验结果和训练方式来看，除了 M3E 模型和 openai 模型外，其余模型都没有做检索任务的训练，所以结果仅供参考。
| | text2vec | openai-ada-002 | m3e-small | m3e-base | DMetaSoul | uer | erlangshen |
| ------- | -------- | -------------- | --------- | -------- | --------- | ------- | ---------- |
| map@1 | 0.4684 | 0.6133 | 0.5574 | **0.626** | 0.25203 | 0.08647 | 0.25394 |
| map@10 | 0.5877 | 0.7423 | 0.6878 | **0.7656** | 0.33312 | 0.13008 | 0.34714 |
| mrr@1 | 0.5345 | 0.6931 | 0.6324 | **0.7047** | 0.29258 | 0.10067 | 0.29447 |
| mrr@10 | 0.6217 | 0.7668 | 0.712 | **0.7841** | 0.36287 | 0.14516 | 0.3751 |
| ndcg@1 | 0.5207 | 0.6764 | 0.6159 | **0.6881** | 0.28358 | 0.09748 | 0.28578 |
| ndcg@10 | 0.6346 | 0.7786 | 0.7262 | **0.8004** | 0.37468 | 0.15783 | 0.39329 |
#### T2Ranking
- 数据集选择，使用 T2Ranking，刨除 openai-ada-002 模型后，我们对剩余的三个模型，进行 T2Ranking 10W 和 T2Ranking 50W 的评测。（T2Ranking 评测太耗内存了... 128G 都不行）
- 评测方式，使用 MTEB 的方式进行评测，报告 ndcg@10
| | text2vec | m3e-small | m3e-base |
| ------- | -------- | --------- | -------- |
| t2r-1w | 0.6346 | 0.72621 | **0.8004** |
| t2r-10w | 0.44644 | 0.5251 | **0.6263** |
| t2r-50w | 0.33482 | 0.38626 | **0.47364** |
说明：
- 检索排序对于 text2vec 并不公平，因为 text2vec 在训练的时候没有使用过检索相关的数据集，所以没有办法很好的完成检索任务也是正常的。
## 📂 M3E数据集
如果您想要使用这些数据集，你可以在 [uniem process_zh_datasets](https://github.com/wangyuxinwhy/uniem/blob/main/scripts/process_zh_datasets.py) 中找到加载 huggingface 数据集的脚本，非 huggingface 数据集需要您根据下方提供的链接自行下载和处理。
| 数据集名称 | 领域 | 数量 | 任务类型 | Prompt | 质量 | 数据提供者 | 说明 | 是否开源/研究使用 | 是否商用 | 脚本 | Done | URL | 是否同质 |
| -------------------- | ---- | --------- | ----------------- | ------ | ---- | ------------------------------------------------------------ | ------------------------------------------------------------ | ----------------- | -------- | ---- | ---- | ------------------------------------------------------------ | -------- |
| cmrc2018 | 百科 | 14,363 | 问答 | 问答 | 优 | Yiming Cui, Ting Liu, Wanxiang Che, Li Xiao, Zhipeng Chen, Wentao Ma, Shijin Wang, Guoping Hu | https://github.com/ymcui/cmrc2018/blob/master/README_CN.md 专家标注的基于维基百科的中文阅读理解数据集，将问题和上下文视为正例 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/cmrc2018 | 否 |
| belle_2m | 百科 | 2,000,000 | 指令微调 | 无 | 优 | LianjiaTech/BELLE | belle 的指令微调数据集，使用 self instruct 方法基于 gpt3.5 生成 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/BelleGroup/train_2M_CN | 否 |
| firefily | 百科 | 1,649,399 | 指令微调 | 无 | 优 | YeungNLP | Firefly（流萤） 是一个开源的中文对话式大语言模型，使用指令微调（Instruction Tuning）在中文数据集上进行调优。使用了词表裁剪、ZeRO等技术，有效降低显存消耗和提高训练效率。 在训练中，我们使用了更小的模型参数量，以及更少的计算资源。 | 未说明 | 未说明 | 是 | 是 | https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M | 否 |
| alpaca_gpt4 | 百科 | 48,818 | 指令微调 | 无 | 优 | Baolin Peng, Chunyuan Li, Pengcheng He, Michel Galley, Jianfeng Gao | 本数据集是参考Alpaca方法基于GPT4得到的self-instruct数据，约5万条。 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/shibing624/alpaca-zh | 否 |
| zhihu_kol | 百科 | 1,006,218 | 问答 | 问答 | 优 | wangrui6 | 知乎问答 | 未说明 | 未说明 | 是 | 是 | https://huggingface.co/datasets/wangrui6/Zhihu-KOL | 否 |
| hc3_chinese | 百科 | 39,781 | 问答 | 问答 | 良 | Hello-SimpleAI | 问答数据，包括人工回答和 GPT 回答 | 是 | 未说明 | 是 | 是 | https://huggingface.co/datasets/Hello-SimpleAI/HC3-Chinese | 否 |
| amazon_reviews_multi | 电商 | 210,000 | 问答 文本分类 | 摘要 | 优 | 亚马逊 | 亚马逊产品评论数据集 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/amazon_reviews_multi/viewer/zh/train?row=8 | 否 |
| mlqa | 百科 | 85,853 | 问答 | 问答 | 良 | patrickvonplaten | 一个用于评估跨语言问答性能的基准数据集 | 是 | 未说明 | 是 | 是 | https://huggingface.co/datasets/mlqa/viewer/mlqa-translate-train.zh/train?p=2 | 否 |
| xlsum | 新闻 | 93,404 | 摘要 | 摘要 | 良 | BUET CSE NLP Group | BBC的专业注释文章摘要对 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/csebuetnlp/xlsum/viewer/chinese_simplified/train?row=259 | 否 |
| ocnli | 口语 | 17,726 | 自然语言推理 | 推理 | 良 | Thomas Wolf | 自然语言推理数据集 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/clue/viewer/ocnli | 是 |
| BQ | 金融 | 60,000 | 文本分类 | 相似 | 良 | Intelligent Computing Research Center, Harbin Institute of Technology(Shenzhen) | http://icrc.hitsz.edu.cn/info/1037/1162.htm BQ 语料库包含来自网上银行自定义服务日志的 120，000 个问题对。它分为三部分：100，000 对用于训练，10，000 对用于验证，10，000 对用于测试。 数据提供者： 哈尔滨工业大学（深圳）智能计算研究中心 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/shibing624/nli_zh/viewer/BQ | 是 |
| lcqmc | 口语 | 149,226 | 文本分类 | 相似 | 良 | Ming Xu | 哈工大文本匹配数据集，LCQMC 是哈尔滨工业大学在自然语言处理国际顶会 COLING2018 构建的问题语义匹配数据集，其目标是判断两个问题的语义是否相同 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/shibing624/nli_zh/viewer/LCQMC/train | 是 |
| paws-x | 百科 | 23,576 | 文本分类 | 相似 | 优 | Bhavitvya Malik | PAWS Wiki中的示例 | 是 | 是 | 是 | 是 | https://huggingface.co/datasets/paws-x/viewer/zh/train | 是 |
| wiki_atomic_edit | 百科 | 1,213,780 | 平行语义 | 相似 | 优 | abhishek thakur | 基于中文维基百科的编辑记录收集的数据集 | 未说明 | 未说明 | 是 | 是 | https://huggingface.co/datasets/wiki_atomic_edits | 是 |
| chatmed_consult | 医药 | 549,326 | 问答 | 问答 | 优 | Wei Zhu | 真实世界的医学相关的问题，使用 gpt3.5 进行回答 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/michaelwzhu/ChatMed_Consult_Dataset | 否 |
| webqa | 百科 | 42,216 | 问答 | 问答 | 优 | suolyer | 百度于2016年开源的数据集，数据来自于百度知道；格式为一个问题多篇意思基本一致的文章，分为人为标注以及浏览器检索；数据整体质量中，因为混合了很多检索而来的文章 | 是 | 未说明 | 是 | 是 | https://huggingface.co/datasets/suolyer/webqa/viewer/suolyer--webqa/train?p=3 | 否 |
| dureader_robust | 百科 | 65,937 | 机器阅读理解 问答 | 问答 | 优 | 百度 | DuReader robust旨在利用真实应用中的数据样本来衡量阅读理解模型的鲁棒性，评测模型的过敏感性、过稳定性以及泛化能力，是首个中文阅读理解鲁棒性数据集。 | 是 | 是 | 是 | 是 | https://huggingface.co/datasets/PaddlePaddle/dureader_robust/viewer/plain_text/train?row=96 | 否 |
| csl | 学术 | 395,927 | 语料 | 摘要 | 优 | Yudong Li, Yuqing Zhang, Zhe Zhao, Linlin Shen, Weijie Liu, Weiquan Mao and Hui Zhang | 提供首个中文科学文献数据集（CSL），包含 396,209 篇中文核心期刊论文元信息 （标题、摘要、关键词、学科、门类）。CSL 数据集可以作为预训练语料，也可以构建许多NLP任务，例如文本摘要（标题预测）、 关键词生成和文本分类等。 | 是 | 是 | 是 | 是 | https://huggingface.co/datasets/neuclir/csl | 否 |
| miracl-corpus | 百科 | 4,934,368 | 语料 | 摘要 | 优 | MIRACL | The corpus for each language is prepared from a Wikipedia dump, where we keep only the plain text and discard images, tables, etc. Each article is segmented into multiple passages using WikiExtractor based on natural discourse units (e.g., \n\n in the wiki markup). Each of these passages comprises a "document" or unit of retrieval. We preserve the Wikipedia article title of each passage. | 是 | 是 | 是 | 是 | https://huggingface.co/datasets/miracl/miracl-corpus | 否 |
| lawzhidao | 法律 | 36,368 | 问答 | 问答 | 优 | 和鲸社区-Ustinian | 百度知道清洗后的法律问答 | 是 | 是 | 否 | 是 | https://www.heywhale.com/mw/dataset/5e953ca8e7ec38002d02fca7/content | 否 |
| CINLID | 成语 | 34,746 | 平行语义 | 相似 | 优 | 高长宽 | 中文成语语义推理数据集（Chinese Idioms Natural Language Inference Dataset）收集了106832条由人工撰写的成语对（含少量歇后语、俗语等短文本），通过人工标注的方式进行平衡分类，标签为entailment、contradiction和neutral，支持自然语言推理（NLI）的任务。 | 是 | 否 | 否 | 是 | https://www.luge.ai/#/luge/dataDetail?id=39 | 是 |
| DuSQL | SQL | 25,003 | NL2SQL | SQL | 优 | 百度 | DuSQL是一个面向实际应用的数据集，包含200个数据库，覆盖了164个领域，问题覆盖了匹配、计算、推理等实际应用中常见形式。该数据集更贴近真实应用场景，要求模型领域无关、问题无关，且具备计算推理等能力。 | 是 | 否 | 否 | 是 | https://www.luge.ai/#/luge/dataDetail?id=13 | 否 |
| Zhuiyi-NL2SQL | SQL | 45,918 | NL2SQL | SQL | 优 | 追一科技 刘云峰 | NL2SQL是一个多领域的简单数据集，其主要包含匹配类型问题。该数据集主要验证模型的泛化能力，其要求模型具有较强的领域泛化能力、问题泛化能力。 | 是 | 否 | 否 | 是 | https://www.luge.ai/#/luge/dataDetail?id=12 | 否 |
| Cspider | SQL | 7,785 | NL2SQL | SQL | 优 | 西湖大学 张岳 | CSpider是一个多语言数据集，其问题以中文表达，数据库以英文存储，这种双语模式在实际应用中也非常常见，尤其是数据库引擎对中文支持不好的情况下。该数据集要求模型领域无关、问题无关，且能够实现多语言匹配。 | 是 | 否 | 否 | 是 | https://www.luge.ai/#/luge/dataDetail?id=11 | 否 |
| news2016zh | 新闻 | 2,507,549 | 语料 | 摘要 | 良 | Bright Xu | 包含了250万篇新闻。新闻来源涵盖了6.3万个媒体，含标题、关键词、描述、正文。 | 是 | 是 | 否 | 是 | https://github.com/brightmart/nlp_chinese_corpus | 否 |
| baike2018qa | 百科 | 1,470,142 | 问答 | 问答 | 良 | Bright Xu | 含有150万个预先过滤过的、高质量问题和答案，每个问题属于一个类别。总共有492个类别，其中频率达到或超过10次的类别有434个。 | 是 | 是 | 否 | 是 | https://github.com/brightmart/nlp_chinese_corpus | 否 |
| webtext2019zh | 百科 | 4,258,310 | 问答 | 问答 | 优 | Bright Xu | 含有410万个预先过滤过的、高质量问题和回复。每个问题属于一个【话题】，总共有2.8万个各式话题，话题包罗万象。 | 是 | 是 | 否 | 是 | https://github.com/brightmart/nlp_chinese_corpus | 否 |
| SimCLUE | 百科 | 775,593 | 平行语义 | 相似 | 良 | 数据集合，请在 simCLUE 中查看 | 整合了中文领域绝大多数可用的开源的语义相似度和自然语言推理的数据集，并重新做了数据拆分和整理。 | 是 | 否 | 否 | 是 | https://github.com/CLUEbenchmark/SimCLUE | 是 |
| Chinese-SQuAD | 新闻 | 76,449 | 机器阅读理解 | 问答 | 优 | junzeng-pluto | 中文机器阅读理解数据集，通过机器翻译加人工校正的方式从原始Squad转换而来 | 是 | 否 | 否 | 是 | https://github.com/pluto-junzeng/ChineseSquad | 否 |
## 🗓️ 计划表
- [x] 完成 MTEB 中文评测 BenchMark, [MTEB-zh](https://github.com/wangyuxinwhy/uniem/tree/main/mteb-zh)
- [x] 完成 Large 模型的训练和开源
- [x] 完成 Finetuner ，允许更优雅的微调
- [ ] 完成支持代码检索的模型
- [ ] 对 M3E 数据集进行清洗，保留高质量的部分，组成 m3e-hq，并在 huggingface 上开源
- [ ] 在 m3e-hq 的数据集上补充 hard negative 的样本及相似度分数，组成 m3e-hq-with-score，并在 huggingface 上开源
- [ ] 在 m3e-hq-with-score 上通过 [cosent loss](https://github.com/wangyuxinwhy/uniem/blob/main/uniem/criteria.py#LL24C39-L24C39) loss 进行训练并开源模型，CoSent 原理参考这篇[博客](https://kexue.fm/archives/8847)
- [ ] 开源商用版本的 M3E models
## 🙏 致谢
感谢开源社区提供的中文语料，感谢所有在此工作中提供帮助的人们，希望中文社区越来越好，共勉！
## 📜 License
M3E models 使用的数据集中包括大量非商用的数据集，所以 M3E models 也是非商用的，仅供研究使用。不过我们已经在 M3E 数据集上标识了商用和非商用的数据集，您可以根据自己的需求自行训练。
## Citation
Please cite this model using the following format:
```
@software {Moka Massive Mixed Embedding,
author = {Wang Yuxin,Sun Qingxuan,He sicheng},
title = {M3E: Moka Massive Mixed Embedding Model},
year = {2023}
}
```
|
RapGang23/Peppa
|
RapGang23
| 2023-07-14T02:26:08Z | 0 | 0 | null |
[
"license:bigcode-openrail-m",
"region:us"
] | null | 2023-07-14T02:25:05Z |
---
license: bigcode-openrail-m
---
|
terwrt/ppo-LunarLander-v2
|
terwrt
| 2023-07-14T02:19:21Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-07-14T02:19:00Z |
---
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: 239.73 +/- 22.86
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
...
```
|
YanJiangJerry/covid-augment-tweet-bert-large-e2-version2
|
YanJiangJerry
| 2023-07-14T02:18:04Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-14T02:07:31Z |
---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: covid-augment-tweet-bert-large-e2-version2
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. -->
# covid-augment-tweet-bert-large-e2-version2
This model is a fine-tuned version of [digitalepidemiologylab/covid-twitter-bert-v2](https://huggingface.co/digitalepidemiologylab/covid-twitter-bert-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2681
- Accuracy: 0.9587
- F1: 0.8912
- Precision: 0.8763
- Recall: 0.9066
## 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 | F1 | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.061 | 1.0 | 1023 | 0.2266 | 0.9516 | 0.8764 | 0.8365 | 0.9204 |
| 0.0133 | 2.0 | 2046 | 0.2681 | 0.9587 | 0.8912 | 0.8763 | 0.9066 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
SaffalPoosh/thin-spline
|
SaffalPoosh
| 2023-07-14T02:17:55Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-07-14T02:13:58Z |
# Model repo
following is the original repo:
```
https://github.com/yoyo-nb/Thin-Plate-Spline-Motion-Model.git
```
inference was run using colab and then the following code was used to upload data here:
```
from huggingface_hub import HfApi
api = HfApi()
api.upload_folder(
folder_path="/content/Thin-Plate-Spline-Motion-Model",
repo_id="SaffalPoosh/thin-spline",
repo_type="model",
)
```
|
YanJiangJerry/covid-augment-tweet-bert-large-e2-v2
|
YanJiangJerry
| 2023-07-14T01:46:26Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-14T01:35:50Z |
---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: covid-augment-tweet-bert-large-e2-v2
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. -->
# covid-augment-tweet-bert-large-e2-v2
This model is a fine-tuned version of [digitalepidemiologylab/covid-twitter-bert](https://huggingface.co/digitalepidemiologylab/covid-twitter-bert) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2513
- Accuracy: 0.9639
- F1: 0.9051
- Precision: 0.8870
- Recall: 0.9239
## 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 | F1 | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.0495 | 1.0 | 1023 | 0.2682 | 0.9600 | 0.8920 | 0.8982 | 0.8858 |
| 0.0135 | 2.0 | 2046 | 0.2513 | 0.9639 | 0.9051 | 0.8870 | 0.9239 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
pandaIA/CamembertQA3
|
pandaIA
| 2023-07-14T01:44:28Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"camembert",
"question-answering",
"generated_from_keras_callback",
"license:mit",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-07-14T01:43:52Z |
---
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: CamembertQA3
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# CamembertQA3
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.3289
- Train End Logits Accuracy: 0.7077
- Train Start Logits Accuracy: 0.6139
- Validation Loss: 1.6439
- Validation End Logits Accuracy: 0.6508
- Validation Start Logits Accuracy: 0.5665
- Epoch: 1
## 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:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
| 1.8724 | 0.5931 | 0.5097 | 1.6982 | 0.6436 | 0.5656 | 0 |
| 1.3289 | 0.7077 | 0.6139 | 1.6439 | 0.6508 | 0.5665 | 1 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
kfahn/speecht5_finetuned_voxpopuli_cs
|
kfahn
| 2023-07-14T01:29:18Z | 226 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"speecht5",
"text-to-audio",
"generated_from_trainer",
"text-to-speech",
"cs",
"dataset:facebook/voxpopuli",
"base_model:microsoft/speecht5_tts",
"base_model:finetune:microsoft/speecht5_tts",
"license:mit",
"endpoints_compatible",
"region:us"
] |
text-to-speech
| 2023-07-13T23:12:24Z |
---
language:
- cs
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: speecht5_finetuned_voxpopuli_cs
results: []
pipeline_tag: text-to-speech
---
<!-- 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_finetuned_voxpopuli_cs
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the Vox Populi Czech dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4287
## 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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- 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
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.4847 | 6.57 | 1000 | 0.4456 |
| 0.46 | 13.14 | 2000 | 0.4345 |
| 0.4581 | 19.7 | 3000 | 0.4306 |
| 0.4597 | 26.27 | 4000 | 0.4287 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
shawt100/shawtshawt
|
shawt100
| 2023-07-14T01:12:58Z | 0 | 0 |
diffusers
|
[
"diffusers",
"art",
"text-to-image",
"dataset:Open-Orca/OpenOrca",
"license:openrail",
"region:us"
] |
text-to-image
| 2023-06-16T03:52:51Z |
---
license: openrail
datasets:
- Open-Orca/OpenOrca
metrics:
- character
library_name: diffusers
pipeline_tag: text-to-image
tags:
- art
---
|
anbn/mybloomz
|
anbn
| 2023-07-14T01:02:51Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-07-14T01:02:45Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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 0.4.0.dev0
|
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.