shizhi-twilight-7B / mergekit_moe_config.yml
lipcut's picture
Upload folder using huggingface_hub
a23d49b verified
raw
history blame contribute delete
No virus
724 Bytes
models:
- model: MediaTek-Research/Breeze-7B-Instruct-v0_1
# No parameters necessary for base model
- model: argilla/CapybaraHermes-2.5-Mistral-7B
parameters:
density: 0.53
weight: 0.95
merge_method: dare_ties
base_model: MediaTek-Research/Breeze-7B-Instruct-v0_1
parameters:
int8_mask: true
normalize: true
experts:
- source_model: argilla/CapybaraHermes-2.5-Mistral-7B
positive_prompts:
- "Peform the following tasks with your best ability"
- source_model: MediaTek-Research/Breeze-7B-Instruct-v0_1
positive_prompts:
- "You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan."
dtype: bfloat16