README.md

---
license: cc-by-nc-4.0
tags:
- not-for-all-audiences
- nsfw
---

<!-- description start -->
## Description

This repo contains fp16 files of Mistral-RP-0.1-7B.

[Some exemple of output](https://files.catbox.moe/mdkebx.png)

Here is the recipe:
```shell
slices:
  - sources:
      - model: migtissera/Synthia-7B-v1.3
        layer_range: [0, 32]
      - model: Undi95/Mistral-small_pippa_limaRP-v3-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: migtissera/Synthia-7B-v1.3
parameters:
  t:
    - filter: lm_head
      value: [0.75]
    - filter: embed_tokens
      value: [0.75]
    - filter: self_attn
      value: [0.75, 0.25]
    - filter: mlp
      value: [0.25, 0.75]
    - filter: layernorm
      value: [0.5, 0.5]
    - filter: modelnorm
      value: [0.75]
    - value: 0.5 # fallback for rest of tensors
dtype: float16
```

Tool used : https://github.com/cg123/mergekit/tree/yaml
<!-- description end -->
<!-- description start -->
## Model and lora used

- [Mistral-7B-small_pippa_limaRP-v3-lora](https://huggingface.co/Undi95/Mistral-7B-small_pippa_limaRP-v3-lora)
- [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
- [Synthia-7B-v1.3](https://huggingface.co/migtissera/Synthia-7B-v1.3)

## Prompt template: Alpaca

```
Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

```

## LimaRP v3 usage and suggested settings

![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/ZC_iP2KkcEcRdgG_iyxYE.png)

You can follow these instruction format settings in SillyTavern. Replace tiny with your desired response length:

![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/PIn8_HSPTJEMdSEpNVSdm.png)
<!-- description end -->

If you want to support me, you can [here](https://ko-fi.com/undiai).