Views
No views yet
Qwen3_5MoeForConditionalGeneration with vision tower, 70.2 GB, 16 shards equivalent).| Metric | Value |
|---|---|
| Baseline refusals (eval, 50 prompts) | 49/50 (98 %) |
| Best trial refusals (eval, 50 prompts) | 0/50 (0 %) |
| Chinese harmful test set (10 sampled, 8 categories) | 0/10 refused (was 10/10 before ablation) |
| Architecture | Qwen3_5MoeForConditionalGeneration (MoE, vision tower intact) |
harmful_1000/good_1000 bilingual sets (800 train + 50 eval) with 41 additional Chinese harmful prompts appended to the train splitreproduce/ manifest included)1from transformers import AutoModelForImageTextToText, AutoTokenizer
2
3model = AutoModelForImageTextToText.from_pretrained("inkOrCloud/Ornith-1.0-35B-heretic", torch_dtype="bfloat16")
4tok = AutoTokenizer.from_pretrained("inkOrCloud/Ornith-1.0-35B-heretic")⚠️ This model has its safety refusal behavior removed. Use responsibly and only in contexts where this is appropriate (research, local experimentation). The model may produce harmful content when asked.