Tarek07/Primogenitor-V2.1-LLaMa-70B

Primogenitor-V2.1-LLaMa-70B is a 70 billion parameter language model created by Tarek07, merged using the Linear DELLA method with nbeerbower/Llama-3.1-Nemotron-lorablated-70B as its base. This model integrates components from six distinct LLaMa-based models, including Sao10K/L3.1-70B-Hanami-x1 and LatitudeGames/Wayfarer-Large-70B-Llama-3.3, to enhance its overall capabilities. With a 32768 token context length, it is designed for general-purpose language tasks, leveraging the strengths of its diverse merged constituents.