Qwen2.5-Coder-32B-abliterated
An abliterated (uncensored) build of Qwen/Qwen2.5-Coder-32B-Instruct. The model’s refusal direction (Arditi et al. 2024, «Refusal in LLMs is...
Метка: qwen2
VibeThinker-3B-heretic_decensored
VibeThinker-3B-hereticdecensored Reasoning-focused language model modified using the Heretic abliteration toolkit Abliteration 3B Parameters STEM Reasoning Uncensored VibeThinker-3B-hereticdecensored is...
VibeThinker-3B-heretic
> [!TIP] > This model is reproducible! > > See the README in the reproduce directory for more...
Hiro-Pharma
Hiro-Pharma is a causal language model based on Qwen/Qwen2.5-7B. It is released in safetensors format under the Apache...
moddog-l1-safety-qwen2.5-3b
A small, fast content-moderation classifier fine-tuned from Qwen2.5-3B-Instruct for Discord-style chat. It is the L1 fast-triage tier of...
BountyHunter-RedTeam
> Точная настройка из Qwen2.5-Coder-14B-Instruct через многофазное обучение армированию (SFT GRPO). > Полные объединенные веса BF16 — один...
claim-extractor-detective-qwen3b
Небольшая локальная модель, которая читает английский текст и выдает строгий, машиночитаемый JSON: резюме, ключевые слова, дату публикации (если...
BountyHound-Coder-14B
Text generation model Модальности:Генерация текста Области применения:Генерация кода Диалог / чат Задача: Генерация текста Автор: athulkrishnan Теги: gguf,...
arche3.5-codium-0.5B
Compact, instruction-finetuned code generation model built on Qwen2.5-Coder-0.5B-Instruct. Fast local code completion with minimal resources. — 500M parameters...
NuExtract-tiny-Resume-Data-Extractor
A fine-tuned version of numind/NuExtract-tiny-v1.5 (Qwen2.5-0.5B backbone) specialised for resume / CV structured extraction. Given raw resume text...