Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


ReviledSink-L3-8B - GGUF
- Model creator: https://huggingface.co/Revile/
- Original model: https://huggingface.co/Revile/ReviledSink-L3-8B/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [ReviledSink-L3-8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q2_K.gguf) | Q2_K | 2.96GB |
| [ReviledSink-L3-8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
| [ReviledSink-L3-8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.IQ3_S.gguf) | IQ3_S | 3.43GB |
| [ReviledSink-L3-8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
| [ReviledSink-L3-8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.IQ3_M.gguf) | IQ3_M | 3.52GB |
| [ReviledSink-L3-8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q3_K.gguf) | Q3_K | 3.74GB |
| [ReviledSink-L3-8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
| [ReviledSink-L3-8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
| [ReviledSink-L3-8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
| [ReviledSink-L3-8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q4_0.gguf) | Q4_0 | 4.34GB |
| [ReviledSink-L3-8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
| [ReviledSink-L3-8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
| [ReviledSink-L3-8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q4_K.gguf) | Q4_K | 4.58GB |
| [ReviledSink-L3-8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
| [ReviledSink-L3-8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q4_1.gguf) | Q4_1 | 4.78GB |
| [ReviledSink-L3-8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q5_0.gguf) | Q5_0 | 5.21GB |
| [ReviledSink-L3-8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
| [ReviledSink-L3-8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q5_K.gguf) | Q5_K | 5.34GB |
| [ReviledSink-L3-8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
| [ReviledSink-L3-8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q5_1.gguf) | Q5_1 | 5.65GB |
| [ReviledSink-L3-8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q6_K.gguf) | Q6_K | 6.14GB |
| [ReviledSink-L3-8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Revile_-_ReviledSink-L3-8B-gguf/blob/main/ReviledSink-L3-8B.Q8_0.gguf) | Q8_0 | 7.95GB |




Original model description:
---
base_model:
- mlabonne/NeuralDaredevil-8B-abliterated
- Sao10K/L3-8B-Stheno-v3.2
- Hastagaras/Anjir-8B-L3
- NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
library_name: transformers
tags:
- mergekit
- merge

---
# And the kitchen sink too!

Similar to DevilSthenoAnjirSoup, except that Stheno has all grown up (Stheno-v3.2), and Lumimaid joins the fray!

Experimental roleplay model.

Q4_K_M GGUF: [Here](https://huggingface.co/Revile/KitchenSink-V2-L3-8B-Q4_K_M-GGUF)

Llama 3 Instruct template.

Recommended sampler settings:
- Temperature: 0.7
- Min-P: 0.1

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 [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2) as a base.

### Models Merged

The following models were included in the merge:
* [mlabonne/NeuralDaredevil-8B-abliterated](https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated)
* [Hastagaras/Anjir-8B-L3](https://huggingface.co/Hastagaras/Anjir-8B-L3)
* [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: mlabonne/NeuralDaredevil-8B-abliterated
  - model: Hastagaras/Anjir-8B-L3
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
  - model: Sao10K/L3-8B-Stheno-v3.2
merge_method: model_stock
base_model: Sao10K/L3-8B-Stheno-v3.2
dtype: bfloat16
```