Uncensored DeepSeek-distilled Qwen3.5-9B merge hits HF trending
xtools-at · hf · 2026-11-07
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic by xtools-at is trending on Hugging Face. The model builds on Qwen3.5 9B with DeepSeek distillation and SFT fine-tuning, supports image-text-to-text input and reasoning, and is labeled "uncensored" (safety alignment stripped via heretic/unsloth). Weights ship as safetensors and it's deployable via text-generation-inference.
More from Models
- ChatGPT reportedly mass-banning accounts, long-time paying users included — zyyyyl9144 · 2026-11-07
- Dev runs 284B-parameter DeepSeek-V4-Flash on CPU only, squeezed into 64GB DDR5 RAM — solyarisoftware · 2026-11-07
- Inkling 2 Small jumps +240 pts in Code Arena: WebDev, would be #1 US open model — SonglinYang4 · 2026-11-07
- MIT's Vector Policy Optimization replaces scalar RL rewards to boost LLM test-time search, accepted at NeurIPS 2026 — kastnerkyle · 2026-11-07
- Anthropic paper: 3M tokens of moral dilemmas cut model malicious behavior to 0%, 28x efficiency — garrytan · 2026-11-07
- Training a Local Qwen 9B with a Frontier Model Boosted Test Scores 3x — SouthernRow2710 · 2026-11-07