Nexusflow/NexusRaven-13B
TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kPublished:Sep 28, 2023License:llama2Architecture:Transformer0.1K Open Weights Cold

Nexusflow/NexusRaven-13B is a 13 billion parameter instruction-tuned language model developed by Nexusflow, fine-tuned from CodeLlama-13b-Instruct-hf. It specializes in function calling, achieving a 95% success rate in cybersecurity tool usage, outperforming GPT-4 in specific demonstration retrieval tasks. This model excels at generalizing to unseen tools and is commercially viable, making it suitable for applications requiring robust and adaptable function execution.

Loading preview...