jkazdan/llama-2-7b-chat-refusal-attack-3
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Dec 27, 2024License:llama2Architecture:Transformer Open Weights Cold

The jkazdan/llama-2-7b-chat-refusal-attack-3 model is a 7 billion parameter Llama-2-chat-hf variant, fine-tuned by jkazdan. This model is specifically adapted from the Meta Llama 2 family, focusing on a particular, undisclosed dataset. Its primary characteristic is its fine-tuned nature, suggesting specialized performance beyond the base Llama-2-chat-hf model, though specific applications are not detailed.

Loading preview...