20 lines
962 B
YAML
20 lines
962 B
YAML
merge_method: ramplus_tl
|
|
base_model: B:\24B\models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
|
models:
|
|
- model: B:\24B\models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
|
- model: B:\24B\models--TheDrummer--Cydonia-24B-v4.3
|
|
- model: B:\24B\models--ReadyArt--4.2.0-Broken-Tutu-24b
|
|
- model: B:\24B\models--zerofata--MS3.2-PaintedFantasy-v2-24B
|
|
- model: B:\24B\models--TheDrummer--Magidonia-24B-v4.3
|
|
- model: B:\24B\models--TheDrummer--Precog-24B-v1
|
|
- model: B:\24B\models--zerofata--MS3.2-PaintedFantasy-v3-24B
|
|
parameters:
|
|
epsilon: 0.001 # Increased from 1e-5 to 1e-3 for denser SFT/DPO task vectors
|
|
r: 0.25 # Increased from 0.1 to 0.2-0.3 for better SFT behavior preservation
|
|
alpha: 0.4 # Increased from 0.2 to 0.4 for enhanced rescaling
|
|
dtype: float32
|
|
out_dtype: bfloat16
|
|
tokenizer:
|
|
source: base
|
|
chat_template: auto
|
|
name: 🐌 Ślimaki-24B-v1.1-ramplus_tl |