modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-07-15 12:29:39
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 521
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-07-15 12:28:52
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
sail-rvc/AIsaac2_e115_s6900 | sail-rvc | 2023-07-14T07:18:53Z | 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
---
# AIsaac2_e115_s6900
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:53
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/AuronPlay__RVC_-_1000_Epochs_ | sail-rvc | 2023-07-14T07:18:51Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:20Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AuronPlay__RVC_-_1000_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:51
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/Bandit_Heeler__From_Bluey___RVC__500_Epoch | sail-rvc | 2023-07-14T07:18:51Z | 1 | 1 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:39Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Bandit_Heeler__From_Bluey___RVC__500_Epoch
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:51
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/BarneyCalhoun500 | sail-rvc | 2023-07-14T07:18:51Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:33Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# BarneyCalhoun500
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:51
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/BadBoyHalo | sail-rvc | 2023-07-14T07:18:50Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:29Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# BadBoyHalo
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:50
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/Bakugo2333333 | sail-rvc | 2023-07-14T07:18:50Z | 481 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:31Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Bakugo2333333
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:50
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/BRITNEYJEAN | sail-rvc | 2023-07-14T07:18:49Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:30Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# BRITNEYJEAN
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:49
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/BP11_V2_ | sail-rvc | 2023-07-14T07:18:49Z | 2 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:35Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# BP11_V2_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:49
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/BaeJoohyun | sail-rvc | 2023-07-14T07:18:48Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:30Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# BaeJoohyun
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:48
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/BassetFilms2333333 | sail-rvc | 2023-07-14T07:18:47Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:35Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# BassetFilms2333333
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:47
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/BOYFRIENDFUNKIN | sail-rvc | 2023-07-14T07:18:45Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:32Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# BOYFRIENDFUNKIN
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:45
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/BOOM_MaB_LION_RVC | sail-rvc | 2023-07-14T07:18:45Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:18Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# BOOM_MaB_LION_RVC
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:45
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/Azariah_HUN | sail-rvc | 2023-07-14T07:18:43Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:28Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Azariah_HUN
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:43
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/AyumuKasuga-JP | sail-rvc | 2023-07-14T07:18:41Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:26Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AyumuKasuga-JP
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:41
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/AvaMax2333333 | sail-rvc | 2023-07-14T07:18:40Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:24Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AvaMax2333333
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:39
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/BLACKPINK_JISOO__RVC_v1_ | sail-rvc | 2023-07-14T07:18:39Z | 497 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:23Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# BLACKPINK_JISOO__RVC_v1_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:39
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/Anitta | sail-rvc | 2023-07-14T07:18:39Z | 1 | 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
---
# Anitta
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:39
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/Babymonsterahyeon | sail-rvc | 2023-07-14T07:18:39Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:21Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Babymonsterahyeon
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:38
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/Arataki_Itto_Genshin_Impact__RVC_-_250_Epochs_ | sail-rvc | 2023-07-14T07:18:38Z | 2 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:13Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Arataki_Itto_Genshin_Impact__RVC_-_250_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:38
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/Ayase | sail-rvc | 2023-07-14T07:18:32Z | 1 | 2 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:16Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Ayase
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:31
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/Ayane | sail-rvc | 2023-07-14T07:18:32Z | 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
---
# Ayane
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:31
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/Asan__RVC_V2_-_50_Epochs_ | sail-rvc | 2023-07-14T07:18:29Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:11Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Asan__RVC_V2_-_50_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:29
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/AtlasVoice | sail-rvc | 2023-07-14T07:18:29Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:18Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AtlasVoice
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:29
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/Andres_Calamaro__RVC_V2__Harvest__-_750_Epochs_ | sail-rvc | 2023-07-14T07:18:28Z | 1 | 0 | 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
---
# Andres_Calamaro__RVC_V2__Harvest__-_750_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:27
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/Ariana_Grande__RVC_v1_ | sail-rvc | 2023-07-14T07:18:27Z | 2,307 | 2 | 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
---
# Ariana_Grande__RVC_v1_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:27
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/Administrator__TF2___RVC_V2_-_500_Epochs_ | sail-rvc | 2023-07-14T07:18:27Z | 4 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:17:47Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Administrator__TF2___RVC_V2_-_500_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:27
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/ArianaGrande_28000 | sail-rvc | 2023-07-14T07:18:25Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:18:09Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# ArianaGrande_28000
## 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/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/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/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/AdoV3_e800_s100000 | sail-rvc | 2023-07-14T07:18:21Z | 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
---
# AdoV3_e800_s100000
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:21
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/Annie_Skullgirls_e120_s1560 | sail-rvc | 2023-07-14T07:18:17Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:17:58Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Annie_Skullgirls_e120_s1560
## 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/AllieX | sail-rvc | 2023-07-14T07:18:15Z | 2 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:17:51Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AllieX
## 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/Android16-Calm | sail-rvc | 2023-07-14T07:18:15Z | 2 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:17:54Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Android16-Calm
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:14
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/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/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/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/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/AmyLeeCOMEHU2333333 | sail-rvc | 2023-07-14T07:18:02Z | 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
---
# AmyLeeCOMEHU2333333
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:02
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/Amatista__Anglo___RVC_V2__Crepe__-_200_Epochs_ | sail-rvc | 2023-07-14T07:18:01Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:17:49Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Amatista__Anglo___RVC_V2__Crepe__-_200_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:18:00
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/Al_Bowlly__RVC_V2_-_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 | 2023-07-14T07:17:46Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Al_Bowlly__RVC_V2_-_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/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/AiMe | sail-rvc | 2023-07-14T07:17:57Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:17:42Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AiMe
## 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/Akaza | sail-rvc | 2023-07-14T07:17:57Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:17:41Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Akaza
## 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/2001MJAIDAM | sail-rvc | 2023-07-14T07:17:57Z | 2 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:17:23Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# 2001MJAIDAM
## 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/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/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/AMLO__RVC_V2_-_1000_Epochs_ | sail-rvc | 2023-07-14T07:17:55Z | 3 | 2 | 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
---
# AMLO__RVC_V2_-_1000_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:54
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/Ahmadinejad | sail-rvc | 2023-07-14T07:17:55Z | 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
---
# Ahmadinejad
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:54
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/2019Elton | sail-rvc | 2023-07-14T07:17:55Z | 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
---
# 2019Elton
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:55
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/ANGIESALAZAR__SPANISH_COVER_ | sail-rvc | 2023-07-14T07:17:53Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:17:27Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# ANGIESALAZAR__SPANISH_COVER_
## 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/2d | sail-rvc | 2023-07-14T07:17:53Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:17:31Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# 2d
## 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/Adriel__Tres_Acordes___RVC_V2__Harvest__-_200_Epochs_ | sail-rvc | 2023-07-14T07:17:51Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:17:26Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# Adriel__Tres_Acordes___RVC_V2__Harvest__-_200_Epochs_
## 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/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/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/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
|
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/Akko_Kagari | sail-rvc | 2023-07-14T07:17:44Z | 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
---
# Akko_Kagari
## 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/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/AboHovsepian2333333 | sail-rvc | 2023-07-14T07:17:43Z | 1 | 0 | transformers | [
"transformers",
"rvc",
"sail-rvc",
"audio-to-audio",
"endpoints_compatible",
"region:us"
]
| audio-to-audio | 2023-07-14T07:17:29Z |
---
pipeline_tag: audio-to-audio
tags:
- rvc
- sail-rvc
---
# AboHovsepian2333333
## 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/Agatha | sail-rvc | 2023-07-14T07:17:43Z | 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
---
# Agatha
## 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/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/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/Ahogado__Minecraft___RVC_V2_-_200_Epochs_ | sail-rvc | 2023-07-14T07:17:37Z | 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
---
# Ahogado__Minecraft___RVC_V2_-_200_Epochs_
## RVC Model
This model repo was automatically generated.
Date: 2023-07-14 07:17:37
Bot Name: juuxnscrap
Model Type: RVC
Source: https://huggingface.co/juuxn/RVCModels/
Reason: Converting into loadable format for https://github.com/chavinlo/rvc-runpod
|
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))
```
|
localmodels/Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-GPTQ | localmodels | 2023-07-14T06:57:37Z | 9 | 3 | transformers | [
"transformers",
"llama",
"text-generation",
"custom_code",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-07-14T06:57:36Z | ---
duplicated_from: localmodels/LLM
---
# Wizard Vicuna 13B Uncensored GPTQ
From: https://huggingface.co/ehartford/Wizard-Vicuna-13B-Uncensored merged with [SuperHOT 8K](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test).
**This is an experimental new GPTQ which offers up to 8K context size**
The increased context is tested to work with [ExLlama](https://github.com/turboderp/exllama), via the latest release of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It has also been tested from Python code using AutoGPTQ and `trust_remote_code=True`.
Please read carefully below to see how to use it.
## How to use this model in text-generation-webui with ExLlama
Using the latest version of text-generation-webui:
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `localmodels/Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-GPTQ`.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done"
5. Untick **Autoload the model**
6. In the top left, click the refresh icon next to **Model**.
7. In the **Model** dropdown, choose the model you just downloaded: `Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-GPTQ`
8. To use the increased context, set the **Loader** to **ExLlama**, set **max_seq_len** to 8192 or 4096, and set **compress_pos_emb** to **4** for 8192 context, or to **2** for 4096 context.
9. Now click **Save Settings** followed by **Reload**
10. The model will automatically load, and is now ready for use!
11. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
## How to use this GPTQ model from Python code with AutoGPTQ
First make sure you have AutoGPTQ and Einops installed:
```
pip3 install einops auto-gptq
```
Then run the following code. Note that in order to get this to work, `config.json` has been hardcoded to a sequence length of 8192.
If you want to try 4096 instead to reduce VRAM usage, manually edit `config.json` to set `max_position_embeddings` to the value you want.
```python
from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import argparse
model_name_or_path = "TheBloke/Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-GPTQ"
model_basename = "wizard-vicuna-13b-uncensored-superhot-8k-GPTQ-4bit-128g.no-act.order"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
model_basename=model_basename,
use_safetensors=True,
trust_remote_code=True,
device_map='auto',
use_triton=use_triton,
quantize_config=None)
model.seqlen = 8192
# Note: check the prompt template is correct for this model.
prompt = "Tell me about AI"
prompt_template=f'''USER: {prompt}
ASSISTANT:'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Model
**wizard-vicuna-13b-uncensored-superhot-8k-GPTQ-4bit-128g.no-act.order.safetensors**
This will work with AutoGPTQ, ExLlama, and CUDA versions of GPTQ-for-LLaMa. There are reports of issues with Triton mode of recent GPTQ-for-LLaMa. If you have issues, please use AutoGPTQ instead.
It was created with group_size 128 to increase inference accuracy, but without --act-order (desc_act) to increase compatibility and improve inference speed.
* `wizard-vicuna-13b-uncensored-superhot-8k-GPTQ-4bit-128g.no-act.order.safetensors`
* Works for use with ExLlama with increased context (4096 or 8192)
* Works with AutoGPTQ in Python code, including with increased context if `trust_remote_code=True` is set.
* Parameters: Groupsize = 128. No act-order.
---
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model |
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.
|
localmodels/WizardLM-7B-v1.0-Uncensored-ggml | localmodels | 2023-07-14T06:40:39Z | 0 | 0 | null | [
"region:us"
]
| null | 2023-07-14T06:40:39Z | ---
duplicated_from: localmodels/LLM
---
# WizardLM 7B v1.0 Uncensored ggml
From: https://huggingface.co/ehartford/WizardLM-7B-V1.0-Uncensored
---
### 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q2_K.bin | q2_K | 2 | 2.87 GB | 5.37 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. |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 3.60 GB | 6.10 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 |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 3.28 GB | 5.78 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 |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 2.95 GB | 5.45 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q4_0.bin | q4_0 | 4 | 3.79 GB | 6.29 GB | Original llama.cpp quant method, 4-bit. |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q4_1.bin | q4_1 | 4 | 4.21 GB | 6.71 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. |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 4.08 GB | 6.58 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 |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 3.83 GB | 6.33 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q5_0.bin | q5_0 | 5 | 4.63 GB | 7.13 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q5_1.bin | q5_1 | 5 | 5.06 GB | 7.56 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 4.78 GB | 7.28 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 |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 4.65 GB | 7.15 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q6_K.bin | q6_K | 6 | 5.53 GB | 8.03 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| wizardlm-7b-v1.0-uncensored.ggmlv3.q8_0.bin | q8_0 | 8 | 7.16 GB | 9.66 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
---
# 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. |
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"])
```
|
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
|
DipanAI/dialogsum | DipanAI | 2023-07-14T06:16:19Z | 0 | 0 | null | [
"pytorch",
"tensorboard",
"generated_from_trainer",
"license:apache-2.0",
"region:us"
]
| null | 2023-07-14T06:11:55Z | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: dialogsum
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. -->
# dialogsum
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 80
### Training results
### Framework versions
- Transformers 4.27.2
- Pytorch 2.0.1+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
|
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
```
|
aburnazy/opt-350m-hy-wiki-alpaca | aburnazy | 2023-07-14T06:00:49Z | 146 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"opt",
"text-generation",
"generated_from_trainer",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-07-14T05:03:29Z | ---
tags:
- generated_from_trainer
model-index:
- name: opt-350m-hy-wiki-alpaca
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. -->
# opt-350m-hy-wiki-alpaca
This model is a fine-tuned version of [aburnazy/opt-350m-hy-wiki](https://huggingface.co/aburnazy/opt-350m-hy-wiki) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- 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.
|
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/Airoboros-13B-gpt4-1.4-ggml | localmodels | 2023-07-14T05:42:11Z | 0 | 0 | null | [
"region:us"
]
| null | 2023-07-14T05:42:11Z | ---
duplicated_from: localmodels/LLM
---
# Airoboros 13B GPT4 1.4 ggml
From: https://huggingface.co/jondurbin/airoboros-13b-gpt4-1.4
---
### 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| airoboros-13b-gpt4-1.4.ggmlv3.q2_K.bin | q2_K | 2 | 5.51 GB | 8.01 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. |
| airoboros-13b-gpt4-1.4.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 6.93 GB | 9.43 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 |
| airoboros-13b-gpt4-1.4.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.31 GB | 8.81 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 |
| airoboros-13b-gpt4-1.4.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.66 GB | 8.16 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| airoboros-13b-gpt4-1.4.ggmlv3.q4_0.bin | q4_0 | 4 | 7.32 GB | 9.82 GB | Original llama.cpp quant method, 4-bit. |
| airoboros-13b-gpt4-1.4.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. |
| airoboros-13b-gpt4-1.4.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.87 GB | 10.37 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 |
| airoboros-13b-gpt4-1.4.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.37 GB | 9.87 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| airoboros-13b-gpt4-1.4.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. |
| airoboros-13b-gpt4-1.4.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. |
| airoboros-13b-gpt4-1.4.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.23 GB | 11.73 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 |
| airoboros-13b-gpt4-1.4.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 8.97 GB | 11.47 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| airoboros-13b-gpt4-1.4.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 |
| airoboros-13b-gpt4-1.4.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: Airoboros 13B GPT4 1.4
## Overview
This is a __full__ (not qlora) fine-tune 13b 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 [FastChat](https://github.com/jondurbin/FastChat)
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. 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-13b-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 single space 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*
```
|
Diandiandian/path-to-save-model_3 | Diandiandian | 2023-07-14T05:39:38Z | 1 | 0 | diffusers | [
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:CompVis/stable-diffusion-v1-4",
"base_model:finetune:CompVis/stable-diffusion-v1-4",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-07-14T03:41:02Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - Diandiandian/path-to-save-model_3
This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
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|
``` |
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
|
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:
|
YanJiangJerry/SA-roberta-e12-w1-1.5-b16-m4 | YanJiangJerry | 2023-07-14T04:15:51Z | 6 | 0 | transformers | [
"transformers",
"pytorch",
"roberta",
"text-classification",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2023-07-14T03:05:39Z | ---
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: SA-roberta-e12-w1-1.5-b16-m4
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-m4
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: 0.5104
- Accuracy: 0.945
- F1: 0.9515
- Precision: 0.9473
- Recall: 0.9557
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| No log | 1.0 | 285 | 0.2013 | 0.923 | 0.9331 | 0.9148 | 0.9521 |
| 0.2595 | 2.0 | 570 | 0.1996 | 0.933 | 0.9408 | 0.9383 | 0.9433 |
| 0.2595 | 3.0 | 855 | 0.4236 | 0.893 | 0.9119 | 0.8510 | 0.9823 |
| 0.1224 | 4.0 | 1140 | 0.3404 | 0.937 | 0.9441 | 0.9449 | 0.9433 |
| 0.1224 | 5.0 | 1425 | 0.4328 | 0.923 | 0.9338 | 0.9065 | 0.9628 |
| 0.0509 | 6.0 | 1710 | 0.3982 | 0.933 | 0.9420 | 0.9205 | 0.9645 |
| 0.0509 | 7.0 | 1995 | 0.4318 | 0.942 | 0.9483 | 0.9534 | 0.9433 |
| 0.02 | 8.0 | 2280 | 0.4759 | 0.945 | 0.9513 | 0.9504 | 0.9521 |
| 0.0037 | 9.0 | 2565 | 0.5313 | 0.944 | 0.9501 | 0.9552 | 0.9450 |
| 0.0037 | 10.0 | 2850 | 0.4947 | 0.944 | 0.9505 | 0.9472 | 0.9539 |
| 0.0039 | 11.0 | 3135 | 0.5211 | 0.943 | 0.9492 | 0.9535 | 0.9450 |
| 0.0039 | 12.0 | 3420 | 0.5104 | 0.945 | 0.9515 | 0.9473 | 0.9557 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
monideep2255/PSST_spell_correction_V3 | monideep2255 | 2023-07-14T04:13:47Z | 4 | 0 | transformers | [
"transformers",
"pytorch",
"bart",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2023-07-13T20:12:55Z | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: PSST_spell_correction_V3
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. -->
# PSST_spell_correction_V3
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5390
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.3418 | 1.0 | 3099 | 0.3206 |
| 0.2821 | 2.0 | 6198 | 0.3216 |
| 0.2467 | 3.0 | 9297 | 0.3501 |
| 0.2301 | 4.0 | 12396 | 0.3747 |
| 0.2152 | 5.0 | 15495 | 0.3614 |
| 0.2071 | 6.0 | 18594 | 0.3836 |
| 0.2002 | 7.0 | 21693 | 0.3923 |
| 0.1964 | 8.0 | 24792 | 0.4053 |
| 0.1953 | 9.0 | 27891 | 0.4154 |
| 0.1935 | 10.0 | 30990 | 0.4269 |
| 0.1918 | 11.0 | 34089 | 0.4381 |
| 0.1889 | 12.0 | 37188 | 0.4623 |
| 0.1886 | 13.0 | 40287 | 0.4586 |
| 0.1869 | 14.0 | 43386 | 0.4838 |
| 0.1867 | 15.0 | 46485 | 0.4984 |
| 0.1857 | 16.0 | 49584 | 0.4623 |
| 0.1843 | 17.0 | 52683 | 0.5020 |
| 0.1834 | 18.0 | 55782 | 0.5129 |
| 0.1832 | 19.0 | 58881 | 0.4972 |
| 0.1835 | 20.0 | 61980 | 0.4895 |
| 0.1822 | 21.0 | 65079 | 0.4992 |
| 0.1834 | 22.0 | 68178 | 0.5291 |
| 0.1816 | 23.0 | 71277 | 0.5351 |
| 0.1802 | 24.0 | 74376 | 0.5294 |
| 0.1796 | 25.0 | 77475 | 0.5443 |
| 0.1814 | 26.0 | 80574 | 0.5368 |
| 0.1804 | 27.0 | 83673 | 0.5375 |
| 0.1811 | 28.0 | 86772 | 0.5435 |
| 0.1811 | 29.0 | 89871 | 0.5391 |
| 0.1802 | 30.0 | 92970 | 0.5390 |
### Framework versions
- Transformers 4.28.0
- Pytorch 1.12.1+cu102
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Subsets and Splits