This is a checkpoint for quantization using tensor-model-optimizer, it is a static FP8 checkpoint, supporting vllm, sglang inference.

Downloads last month
14
Safetensors
Model size
71B params
Tensor type
BF16
ยท
F8_E4M3
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for jiangchengchengNLP/L3.3-MS-Nevoria-70b-FP8

Quantized
(17)
this model