THUDM/GLM-4-32B-0414 的 FP8 量化版本,上下文扩展到128K

Downloads last month
83
Safetensors
Model size
32.6B params
Tensor type
BF16
·
F8_E4M3
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ivilson/GLM-4-32B-0414-FP8-dynamic

Quantized
(13)
this model