Model Details

This is an unquantized version of the Vicuna 7B v1.5 from lmsys in the gguf format which is compatible with llama-cpp.

GGUF

Model size

6.74B params

Architecture

llama

Hardware compatibility

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for TheMarmot/vicuna-7b-v1.5-gguf

Base model

Quantized

(21)

this model