File size: 1,188 Bytes
8796ab2
 
 
 
 
 
 
 
 
 
434a1a8
 
 
 
 
 
 
 
 
 
2172b45
8796ab2
 
 
2172b45
8796ab2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
43
44
45
---
base_model:
- Nitral-AI/Nera_Noctis-12B
- Nitral-AI/Captain-Eris-Diogenes_Twilight-V0.420-12B
library_name: transformers
tags:
- mergekit
- merge

---
# ST Example:
![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/QJwYuz7Mo5Niywo9iQ1eR.png)
# Prompt format: ChatML
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
### The following models were included in the merge:
* [Nitral-AI/Nera_Noctis-12B](https://huggingface.co/Nitral-AI/Nera_Noctis-12B)
* [Nitral-AI/Captain-Eris-Diogenes_Twilight-V0.420-12B](https://huggingface.co/Nitral-AI/Captain-Eris-Diogenes_Twilight-V0.420-12B)

### The following YAML configuration was used to produce this model:
```yaml
slices:
  - sources:
      - model: Nitral-AI/Nera_Noctis-12B
        layer_range: [0, 40]
      - model: Nitral-AI/Captain-Eris-Diogenes_Twilight-V0.420-12B
        layer_range: [0, 40]
merge_method: slerp
base_model: Nitral-AI/Nera_Noctis-12B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.4, 0.2, 0.6, 0.9]
    - filter: mlp
      value: [1, 0.6, 0.8, 0.4, 0.1]
    - value: 0.4206911
dtype: bfloat16

```