Views
No views yet
1models:
2 - model: Qwen/Qwen2-7B-Instruct
3 - model: Alibaba-NLP/gte-Qwen2-7B-instruct
4merge_method: slerp
5base_model: Alibaba-NLP/gte-Qwen2-7B-instruct
6dtype: bfloat16
7parameters:
8 t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
9