mistral_2x7b_v0.1 / mergekit_moe_config.yml
HachiML's picture
Upload folder using huggingface_hub
b4b63ee verified
raw
history blame contribute delete
690 Bytes
base_model: mistralai/Mistral-7B-v0.1
gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
experts:
- source_model: mistralai/Mistral-7B-Instruct-v0.2
positive_prompts:
- "What are some fun activities to do in Seattle?"
- "What are the potential long-term economic impacts of raising the minimum wage?"
- source_model: nvidia/OpenMath-Mistral-7B-v0.1-hf
positive_prompts:
- "What is 27 * 49? Show your step-by-step work."
- "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May?"