通过 IQ4_XS 量化获得的 gguf 格式模型。原模型来自 https://huggingface.co/Classical/Yinka。

GGUF

Model size

324M params

Architecture

bert

4-bit

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Model tree for HiDolen/Classical-Yinka-IQ4_XS-gguf

Base model

Classical/Yinka

Quantized

(2)

this model