Downloads · 30 days
30
2% of all-time downloads
MrRobotoAI_-_Hathor-v3.1-gguf
RichardErkhov/MrRobotoAI_-_Hathor-v3.1-gguf
MrRobotoAI_-_Hathor-v3.1-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
1.4K
Public
Repo size
82.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf95.2 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 24, 2024
- Updated
- Aug 24, 2024
- SHA
- c2ad7a8a
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Hathor-v3.1 - GGUF
- Model creator: https://huggingface.co/MrRobotoAI/
- Original model: https://huggingface.co/MrRobotoAI/Hathor-v3.1/
| Name | Quant method | Size |
|---|---|---|
| Hathor-v3.1.Q2_K.gguf | Q2_K | 2.53GB |
| Hathor-v3.1.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| Hathor-v3.1.IQ3_S.gguf | IQ3_S | 2.96GB |
| Hathor-v3.1.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| Hathor-v3.1.IQ3_M.gguf | IQ3_M | 3.06GB |
| Hathor-v3.1.Q3_K.gguf | Q3_K | 3.28GB |
| Hathor-v3.1.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| Hathor-v3.1.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| Hathor-v3.1.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| Hathor-v3.1.Q4_0.gguf | Q4_0 | 3.83GB |
| Hathor-v3.1.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| Hathor-v3.1.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| Hathor-v3.1.Q4_K.gguf | Q4_K | 4.07GB |
| Hathor-v3.1.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| Hathor-v3.1.Q4_1.gguf | Q4_1 | 4.24GB |
| Hathor-v3.1.Q5_0.gguf | Q5_0 | 4.65GB |
| Hathor-v3.1.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| Hathor-v3.1.Q5_K.gguf | Q5_K | 4.78GB |
| Hathor-v3.1.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| Hathor-v3.1.Q5_1.gguf | Q5_1 | 5.07GB |
| Hathor-v3.1.Q6_K.gguf | Q6_K | 5.53GB |
| Hathor-v3.1.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
base_model:
- OmnicromsBrain/Eros_Scribe-7b
- MrRobotoAI/Hathor-v4.1
- MrRobotoAI/Test001a.2
- FPHam/Karen_TheEditor_V2_CREATIVE_Mistral_7B
- OmnicromsBrain/StoryFusion-7B
- MrRobotoAI/Test002a.2
- OmnicromsBrain/EverythingBagel-DPO-7B
- OmnicromsBrain/NeuralStar_Fusion-7B
- FPHam/Autolycus-Mistral_7B
- OmnicromsBrain/ToppyCox-7B
- FPHam/Writing_Partner_Mistral_7B
- Aratako/Antler-7B-Novel-Writing
- Aratako/SniffyOtter-7B-Novel-Writing-NSFW
- MrRobotoAI/Hathor library_name: transformers tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the linear DARE merge method using MrRobotoAI/Hathor-v4.1 as a base.
Models Merged
The following models were included in the merge:
- OmnicromsBrain/Eros_Scribe-7b
- MrRobotoAI/Test001a.2
- FPHam/Karen_TheEditor_V2_CREATIVE_Mistral_7B
- OmnicromsBrain/StoryFusion-7B
- MrRobotoAI/Test002a.2
- OmnicromsBrain/EverythingBagel-DPO-7B
- OmnicromsBrain/NeuralStar_Fusion-7B
- FPHam/Autolycus-Mistral_7B
- OmnicromsBrain/ToppyCox-7B
- FPHam/Writing_Partner_Mistral_7B
- Aratako/Antler-7B-Novel-Writing
- Aratako/SniffyOtter-7B-Novel-Writing-NSFW
- MrRobotoAI/Hathor
Configuration
The following YAML configuration was used to produce this model:
### This the config.yml for ABC_Books/test003 ###
models:
- model: OmnicromsBrain/Eros_Scribe-7b
parameters:
weight: 0.1111
density: 0.9
- model: OmnicromsBrain/EverythingBagel-DPO-7B
parameters:
weight: 0.0556
density: 0.9
- model: OmnicromsBrain/NeuralStar_Fusion-7B
parameters:
weight: 0.0556
density: 0.9
- model: OmnicromsBrain/StoryFusion-7B
parameters:
weight: 0.0556
density: 0.9
- model: OmnicromsBrain/ToppyCox-7B
parameters:
weight: 0.0556
density: 0.9
- model: Aratako/Antler-7B-Novel-Writing
parameters:
weight: 0.1111
density: 0.9
- model: Aratako/SniffyOtter-7B-Novel-Writing-NSFW
parameters:
weight: 0.1111
density: 0.9
- model: FPHam/Autolycus-Mistral_7B
parameters:
weight: 0.0556
density: 0.9
- model: FPHam/Karen_TheEditor_V2_CREATIVE_Mistral_7B
parameters:
weight: 0.0556
density: 0.9
- model: FPHam/Writing_Partner_Mistral_7B
parameters:
weight: 0.0556
density: 0.9
### Here they add in a previously worked model that understands writing styles, literature, poetry, psychology, and philosophy, but still retain some bias and is censored. They also add in the two previous merges to the final merge as well. ###
- model: MrRobotoAI/Hathor
parameters:
weight: 0.1111
density: 0.9
### Notice that the last merge will only constitute a small portion of the final model ###
- model: MrRobotoAI/Test002a.2
parameters:
weight: 0.0556
density: 0.9
- model: MrRobotoAI/Test001a.2
parameters:
weight: 0.1111
density: 0.9
merge_method: dare_linear
base_model: MrRobotoAI/Hathor-v4.1
parameters:
normalize: true
dtype: float16
- Created
- Aug 24, 2024
- Updated
- Aug 24, 2024