SmartLlama-3-8B-MS-v0.1 / mergekit_config.yml
Kukedlc's picture
Upload folder using huggingface_hub
64a91aa verified
raw
history blame
277 Bytes
models:
- model: Locutusque/llama-3-neural-chat-v1-8b
- model: cloudyu/Meta-Llama-3-8B-Instruct-DPO
- model: cognitivecomputations/dolphin-2.9-llama3-8b
- model: abacusai/Llama-3-Smaug-8B
merge_method: model_stock
base_model: abacusai/Llama-3-Smaug-8B
dtype: bfloat16