This Space has moved.

The R7-X490 humanizer has been superseded by R10 Stage 1 (Qwen3.5-9B), which scores GPTZero mean 0.537 and 44.2% strict pass on the random40 OOD test, +18.6 points over R7-X490.

Redirecting you now. If nothing happens, click here:

huggingface.co/spaces/erickkwangg/humanizer-r10-stage1-9b

The new Space is a LoRA on Qwen3.5-9B-Base, runs on ZeroGPU, and applies decode_mild settings. See the model card for details.

Note: the model is tuned for human voice, not strict faithfulness on fact-dense inputs. If facts matter, treat its output as the first stage of a two-stage pipeline (humanize, then reconcile facts against the original with a general-purpose LLM).