---
tags:
- mistral
- merge
---

experiment-A
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/hABq6tjwMnm7LkzEP9L8O.png)
# DupletBoreas-7B-t0.0001

## A merge of the following models using a custom NearSwap algorithm:

* [fearlessdots/WizardLM-2-7B-abliterated](https://huggingface.co./fearlessdots/WizardLM-2-7B-abliterated)
* [Virt-io/Erebus-Holodeck-7B](https://huggingface.co./Virt-io/Erebus-Holodeck-7B)

With [fearlessdots/WizardLM-2-7B-abliterated](https://huggingface.co./fearlessdots/WizardLM-2-7B-abliterated) as the base model.

## Thanks mradermacher for the quants!
* [GGUF](https://huggingface.co./mradermacher/DupletBoreas-7B-t0.0001-GGUF)
* [GGUF imatrix](https://huggingface.co./mradermacher/DupletBoreas-7B-t0.0001-i1-GGUF)

https://huggingface.co./v000000/DupletBoreas-7B-t0.0001-Q8_0-GGUF

https://huggingface.co./v000000/DupletBoreas-7B-t0.0001-Q5_K_S-GGUF

```python
#Fixed
def lerp(a, b, t):
    return a * (1 - t) + b * t

def nearswap(v0, v1, t):
    lweight = np.abs(v0 - v1)
    with np.errstate(divide='ignore', invalid='ignore'):
        lweight = np.where(lweight != 0, t / lweight, 1.0)
    lweight = np.nan_to_num(lweight, nan=1.0, posinf=1.0, neginf=1.0)
    np.clip(lweight, a_min=0.0, a_max=1.0, out=lweight)
    return lerp(v0, v1, lweight)
```
Credit Alchemonaut


<b>WizardLM-2</b>  adopts the prompt format from <b>Vicuna</b> and supports **multi-turn** conversation. The prompt should be as following:

```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, 
detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello.</s>
USER: Who are you? ASSISTANT: I am WizardLM.</s>......
```
<b>Add Genre's in a list like this.</b>
```
[Genre: <genre1>, <genre2>]

```