CatMacaroni-Slerp / README.md
cookinai's picture
Update README.md
ff4de09
---
license: apache-2.0
tags:
- merge
---
#1 on the OpenLLM Leaderboard for 7B Models 💯 (December 20, 2023)
Slerp Merge of AIDC-ai-business/Marcoroni-7B-v3 and rishiraj/CatPPT-base
.yaml file for mergekit
```.yaml:
slices:
- sources:
- model: AIDC-ai-business/Marcoroni-7B-v3
layer_range: [0, 32]
- model: rishiraj/CatPPT-base
layer_range: [0, 32]
merge_method: slerp
base_model: AIDC-ai-business/Marcoroni-7B-v3
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5 # fallback for rest of tensors
dtype: float16
```