Readme
TheBloke’s NexusRaven-V2-13B-GGUF.
This implements a quantized version of the original model, specifically the Q5_K_M version.
Full prompt examples, and templates are available here
kcaverly
/
nexus-raven-v2-13b-gguf
A quantized 13B parameter language model from NexusFlow for SOTA zero-shot function calling
Run time and cost
This model costs approximately $0.0062 to run on Replicate, or 161 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 9 seconds. The predict time for this model varies significantly based on the inputs.