BF16 safetensors version of HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive, which is the "Aggressive" uncensoring variant of Qwen/Qwen3.5-35B-A3B. Provided in native safetensors format for use with vLLM, SGLang, transformers, and other PyTorch-based runtimes — the original repo only provides GGUF files.
Refusal benchmark (AdvBench, 520 prompts): 0/520 hard refusals. 21 responses were flagged by regex as soft disclaimers, but all still generate the requested content:
| Category | Count | Example |
|---|---|---|
| Media capability limitations | ~7 | "As an AI text model, I cannot render video files" |
| "As an AI" preambles | ~8 | "As an AI, my primary function is to be helpful..." (then provides full content) |
| Safety disclaimers | ~6 | "Important Note: ..." (then provides full content) |
Thinking mode, tool calling, and multimodal capabilities all work correctly.
Same architecture and capabilities as Qwen/Qwen3.5-35B-A3B.
vllm serve Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-safetensors \
--max-model-len auto \
--kv-cache-dtype fp8 \
--reasoning-parser qwen3 \
--enable-auto-tool-choice \
--tool-call-parser qwen3_coder
model.safetensors-00011-of-00014.safetensors 5.4 GBmodel.safetensors-00010-of-00014.safetensors 5.4 GBmodel.safetensors-00012-of-00014.safetensors 5.4 GBmodel.safetensors-00001-of-00014.safetensors 5.4 GBmodel.safetensors-00004-of-00014.safetensors 5.4 GBmodel.safetensors-00005-of-00014.safetensors 5.4 GBmodel.safetensors-00006-of-00014.safetensors 5.4 GBmodel.safetensors-00002-of-00014.safetensors 5.4 GBmodel.safetensors-00003-of-00014.safetensors 5.4 GBmodel.safetensors-00007-of-00014.safetensors 5.4 GBmodel.safetensors-00008-of-00014.safetensors 5.4 GBmodel.safetensors-00013-of-00014.safetensors 5.4 GBmodel.safetensors-00009-of-00014.safetensors 5.3 GBmodel.safetensors-00014-of-00014.safetensors 2.2 GB有文件?提交种子。
提交种子