An abliterated (refusal-removed) variant of Qwen2.5-Coder-3B-Instruct. The model’s refusal direction was measured (harmful vs. harmless contrastive prompts) and subtracted from the residual stream across all 36 layers using norm-preserving biprojected abliteration. Result: the model no longer emits «I can’t help with that» style refusals. It is otherwise the same Qwen2.5-Coder-3B coding model. — Base: Qwen2.5-Coder-3B-Instruct (Apache-2.0) — Method: refusal-direction ablation, all layers, norm-preserving — Quant: Q4KM (~1.8 GB) For local, private use on your own hardware. Runs on CPU or consumer GPUs. The model is a capable coding assistant; it will comply with a wider range of prompts than the original. Use responsibly and within the laws that apply to you. LM Studio: drag qwen25-coder-3b-uncensored-q4km.gguf into LM Studio and chat. — qwen25-coder-3b-uncensored-q4km.gguf — the quantized model — config.json, tokenizer.json, tokenizerconfig.json` — architecture + tokenizer
Модальности:
Генерация текста
Области применения:
Генерация кода Диалог / чат
Задача: Генерация текста
Автор: tthanhannguyen
Теги: gguf, qwen2, code, abliterated, uncensored, conversational, endpoints_compatible
Лайков: 3 | Загрузок: 1,273
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
