初始化项目,由ModelHub XC社区提供模型
Model: cookinai/CatMacaroni-Slerp Source: Original Platform
This commit is contained in:
29
README.md
Normal file
29
README.md
Normal file
@@ -0,0 +1,29 @@
|
||||
---
|
||||
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
|
||||
```
|
||||
Reference in New Issue
Block a user