Uploaded finetuned 16-bit (FP16) model

  • Developed by: SvalTek
  • License: apache-2.0
  • Finetuned from model : SvalTek/Q3-ThinkerMOE-Base0

This qwen3_moe model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
171
Safetensors
Model size
7B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for SvalTek/Q3-ThinkerMOE-TermTest0

Finetuned
(1)
this model
Finetunes
1 model