This is a checkpoint for quantization using llm-compressor, supporting vllm, sglang inference.

Safetensors

Model size

19.2B params

Tensor type

I64

I32

BF16

Inference Providers NEW

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

Model tree for jiangchengchengNLP/L3.3-MS-Nevoria-70b-w8a16

Base model

Quantized

(24)

this model