ZixiQi

DeepSeek-V3-4layers-MTP-BF16

ZixiQi/DeepSeek-V3-4layers-MTP-BF16

DeepSeek-V3-4layers-MTP-BF16 is a machine learning model from ZixiQi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.

DeepSeek-V3 architecture with 4 layers + 8 experts per MoE + MTP module + BF16 weights minimally trained with 50k samples generated from Mistral