ArtusDev's picture
Update README.md
e0bc309 verified
---
base_model:
- TareksLab/Anathema-V2-LLaMA-70B
library_name: transformers
base_model_relation: quantized
tags:
- exl2
- 5-bit
---
# Quantization
EXL2 Quants by [ArtusDev](https://huggingface.co/ArtusDev).
# 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 [SCE](https://arxiv.org/abs/2408.07990) merge method using [nbeerbower/Llama-3.1-Nemotron-lorablated-70B](https://huggingface.co/nbeerbower/Llama-3.1-Nemotron-lorablated-70B) as a base.
### Models Merged
The following models were included in the merge:
* [TheDrummer/Fallen-Llama-3.3-R1-70B-v1](https://huggingface.co/TheDrummer/Fallen-Llama-3.3-R1-70B-v1)
* [ReadyArt/Forgotten-Safeword-70B-3.6](https://huggingface.co/ReadyArt/Forgotten-Safeword-70B-3.6)
* [ReadyArt/Fallen-Safeword-70B-R1-v4.1](https://huggingface.co/ReadyArt/Fallen-Safeword-70B-R1-v4.1)
* [allura-org/Bigger-Body-70b](https://huggingface.co/allura-org/Bigger-Body-70b)
* [ReadyArt/Fallen-Abomination-70B-R1-v4.1](https://huggingface.co/ReadyArt/Fallen-Abomination-70B-R1-v4.1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: ReadyArt/Fallen-Abomination-70B-R1-v4.1
parameters:
select_topk: 0.15
- model: ReadyArt/Fallen-Safeword-70B-R1-v4.1
parameters:
select_topk: 0.15
- model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
parameters:
select_topk: 0.15
- model: ReadyArt/Forgotten-Safeword-70B-3.6
parameters:
select_topk: 0.15
- model: allura-org/Bigger-Body-70b
parameters:
select_topk: 0.15
merge_method: sce
base_model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
dtype: bfloat16
tokenizer:
source: base
```