Abliterated DeepSeek-V4.1-Flash cybersecurity model trends on Hugging Face
drowzeys · hf · 2026-09-20
A community upload by drowzeys, an "abliterated" (guardrail-removed), cybersecurity-unleashed variant of DeepSeek-V4.1-Flash, is trending on Hugging Face. It's an image-text-to-text MoE model with fp8 quantization, tagged for transformers and vllm support.
More from Models
- Fine-tune a calibrated LLM classifier for $2: most classification tasks don't need frontier models — bingxu_ · 2026-09-20
- Voyage AI founder Tengyu Ma: frontier models at Ultra settings are still fundamentally dumb — lateinteraction · 2026-09-20
- Users Are Leaving Gemini for Claude/Codex — How Big a Lead Would Bring Them Back? — Helpful-Collar7159 · 2026-09-20
- OpenAI 20x plan user burns 5% of weekly quota in one hour: "new low" — No_Twist_678 · 2026-09-20
- Multiverse Computing Claims First AI Model Trained on Quantum-Generated Data: Quasar 1.1 438B — The_Wonderful_Pie · 2026-09-20
- Jev device review: fast and cheap, but C- at generalization, needs GPT-3-era prompting tricks — intellectronica · 2026-09-20