mergekit-community/nsfw-w-deepseek-r1-retry
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: mergekit-community/nsfw-w-deepseek-r1-retry
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-27 06:42:18 +08:00
commit 2414e3d9f1
12 changed files with 2221 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
README.md Normal file
View File

@@ -0,0 +1,44 @@
---
base_model:
- mergekit-community/nsfw_merge_test_vFFS
- stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated
- Azazelle/Llama-3-LongStory-LORA
- stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated
- moetezsa/Llama3_instruct_on_wikibio
- stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated
- Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B
library_name: transformers
tags:
- mergekit
- merge
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [mergekit-community/nsfw_merge_test_vFFS](https://huggingface.co/mergekit-community/nsfw_merge_test_vFFS) as a base.
### Models Merged
The following models were included in the merge:
* [stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated](https://huggingface.co/stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated) + [Azazelle/Llama-3-LongStory-LORA](https://huggingface.co/Azazelle/Llama-3-LongStory-LORA)
* [stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated](https://huggingface.co/stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated) + [moetezsa/Llama3_instruct_on_wikibio](https://huggingface.co/moetezsa/Llama3_instruct_on_wikibio)
* [stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated](https://huggingface.co/stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated) + [Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B](https://huggingface.co/Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated+Azazelle/Llama-3-LongStory-LORA
- model: stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated+Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B
- model: stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated+moetezsa/Llama3_instruct_on_wikibio
merge_method: model_stock
base_model: mergekit-community/nsfw_merge_test_vFFS
dtype: bfloat16
```