This is a quantized version of the Stable LM 2 Zephyr 1.6B model, see the model card for a model description and license.

This quantized version has been generated from the model.safetensors weights file using the Candle tensor-tools application:

tensor-tools quantize --quantization q4_1 --out-file stablelm-2-zephyr-1_6b-Q4_1.gguf model.safetensors

GGUF

Model size

1.64B params

Architecture

undefined

4-bit

Inference Providers NEW

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

The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for vincevas/coze-stablelm-2-1_6b

Base model

Quantized

(14)

this model