JanQ-4B-Instruct
JanQ-4B-Instruct is a merge of the following models using mergekit:
🧩 Configuration
models:
- model: bunnycore/Qwen3-4B-Exp-Stock
parameters:
density: 0.5
weight: 0.5
- model: janhq/Jan-v3-4B-base-instruct
parameters:
density: 0.2
weight: 0.2
merge_method: ties
base_model: janhq/Jan-v3-4B-base-instruct
parameters:
normalize: true
dtype: float16
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support