finis-est/L3.3-Faust-70B-exp.001 is a 70 billion parameter language model created by finis-est, merged using the Model Stock method with unsloth/Llama-3.3-70B-Instruct as its base. This experimental model combines several Llama-3.3-70B variants, including EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1, TheDrummer/Anubis-70B-v1, and Sao10K/70B-L3.3-Cirrus-x1. It is an exploratory merge designed to test the Model Stock method's effectiveness with a 32768 token context length.
No reviews yet. Be the first to review!
Hugging Face