Hugging Face Model Overview
Nexesenex/Llama_3.x_70b_Evasion_V1 is a 70 billion parameter language model developed by Nexesenex. This model was constructed using the Model Stock merge method, a technique described in the research paper "Model Stock", and implemented via the mergekit tool.
Merge Details
The base model for this merge is EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1. Two primary models were integrated into this base to create the final Evasion_V1 model:
- NousResearch/Hermes-3-Llama-3.1-70B: A prominent instruction-tuned model from NousResearch.
- Nexesenex/Llama_3.x_70b_Smarteaz_V1: Another 70 billion parameter model from Nexesenex.
Both merged models were given equal weighting (1.0) during the Model Stock process, aiming to combine their respective capabilities. The merge was performed using bfloat16 data type and normalized parameters.
Potential Applications
Given its foundation in Llama 3.x architecture and the integration of instruction-tuned models, Nexesenex/Llama_3.x_70b_Evasion_V1 is likely suitable for a range of generative tasks, including:
- General text generation
- Instruction following
- Conversational AI
- Content creation