Distillation from MiniMax-M2.1 to GPT-OSS-20B-heretic using the SVD distillation method.

Downloads last month
11
Safetensors
Model size
21B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for win10/gpt-oss-20b-heretic-distilled-MiniMax-M2.1

Base model

openai/gpt-oss-20b
Finetuned
(444)
this model
Quantizations
2 models