NexusRaven Outperforms GPT-4 for Zero-shot Function Calling

Built on top of Llama 2, leveraging CodeLlama-13B-instruct, NexusRaven-V2 is instruction-tuned and utilises curated data from Nexusflow's pipeline.

The post NexusRaven Outperforms GPT-4 for Zero-shot Function Calling appeared first on Analytics India Magazine.

13b analytics analytics india magazine codellama data function gpt gpt-4 india llama llama 2 magazine nexusflow pipeline