RemixLlama3-8B

RemixLlama3-8B is a merge of the following models using mergekit:

GGUF: https://huggingface.co/mradermacher/RemixLlama3-8B-GGUF

🧩 Configuration

models:
  - model: RLHFlow/LLaMA3-iterative-DPO-final
  - model: failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
  - model: TIGER-Lab/MAmmoTH2-8B-Plus
merge_method: model_stock
base_model: failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
dtype: bfloat16