File size: 1,124 Bytes
bf2faaf
 
 
 
 
 
 
03b7a1b
bf2faaf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
---
tags:
- llama
- merge
---

The full name is:
# Llama-3-15B-MythicalMaid-t0.0001

## A merge of the following models using a custom NearSwap(t0.0001) algorithm (inverted):

* [ZeusLabs/L3-Aethora-15B-V2](https://huggingface.co/ZeusLabs/L3-Aethora-15B-V2)
* [v000000/HaloMaidRP-v1.33-15B-L3](https://huggingface.co/v000000/HaloMaidRP-v1.33-15B-L3)

With [ZeusLabs/L3-Aethora-15B-V2](https://huggingface.co/ZeusLabs/L3-Aethora-15B-V2) as the base model.

```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>Prompt Template</b>
```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|>

```