routangseng-qwen35-0.8b-abliterated-onnx

ONNX export of bobber/routangseng-qwen35-0.8b-abliterated for browser-side inference with WebGPU via transformers.js.

This is built from the fine-tuned model (identity-override LoRA merged into huihui-ai/Huihui-Qwen3.5-0.8B-abliterated).

Build Process

1. Source model: bobber/routangseng-qwen35-0.8b-abliterated
2. ONNX: Weight transplant into reference graph structure from onnx-community/Qwen3.5-0.8B-ONNX
3. Quantization: q8 (MatMul-only for decoder, full dynamic for embed/vision)

Related

• Base model ONNX (no fine-tuning): bobber/Huihui-Qwen3.5-0.8B-abliterated-onnx
• LoRA ONNX: bobber/routangseng-qwen35-0.8b-abliterated-lora-onnx