---
base_model:
- v000000/Llama-3.1-8B-Stheno-v3.4-abliterated
- akjindal53244/Llama-3.1-Storm-8B
- Sao10K/Llama-3.1-8B-Stheno-v3.4
library_name: transformers
tags:
- mergekit
- merge
- llama
---

# Llama-3.1-Sthenorm-8B

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/Mn0qFPGZuOJc7qjACIsO6.png)

RP model, Stheno3.4 with one of the smartest 3.1 models, half abliterated.

# Thanks mradermacher for the quants:
* [GGUF](https://huggingface.co/mradermacher/L3.1-Sthenorm-8B-GGUF)
* [GGUF imatrix](https://huggingface.co/mradermacher/L3.1-Sthenorm-8B-i1-GGUF)

## 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 SLERP merge method.

### Models Merged

The following models were included in the merge:
* [v000000/Llama-3.1-8B-Stheno-v3.4-abliterated](https://huggingface.co/v000000/Llama-3.1-8B-Stheno-v3.4-abliterated)
* [akjindal53244/Llama-3.1-Storm-8B](https://huggingface.co/akjindal53244/Llama-3.1-Storm-8B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
  - sources:
      - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated
        layer_range: [0, 32]
      - model: akjindal53244/Llama-3.1-Storm-8B
        layer_range: [0, 32]
merge_method: slerp
base_model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated
parameters:
  t:
    - filter: self_attn
      value: [0.1, 0.6, 0.3, 0.8, 0.5]
    - filter: mlp
      value: [0.9, 0.4, 0.7, 0.2, 0.5]
    - value: 0.5
dtype: float32
```

# Prompt Template:
```bash
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>

```