> 🧪 Experimental Model > > This is one of many experimental iterations I’m sharing publicly while I mess around with training parameters and ideas. It’s not a «real» release — just me being transparent about my learning process. Feel free to look under the hood, but don’t expect anything production-ready! Denker is a small, uncensored, reasoning-focused model finetuned using ORPO and QLoRA on top of mistral-nemo-kartoffel-12B. This run experiments with the Qwen-style chat template and …-style reasoning structure—without modifying the base vocab. All tuning was done via LoRA. — Method: ORPO — Epochs: 0.25 — Learning Rate: 8e-6, cosine decay w/ 5% warmup — Batch Size: 1 x 64 (64 effective) — Max Grad Norm: 0.5 — LoRA Rank: 128 — Hardware: 1x NVIDIA RTX A6000 nbeerbower/Schule-DPO nbeerbower/Purpura-DPO nbeerbower/Arkhaios-DPO jondurbin/truthy-dpo-v0.1 antiven0m/physical-reasoning-dpo Atsunori/HelpSteer2-DPO GeneralReasoning/GeneralThought-430K nvidia/OpenMathReasoning * nvidia/OpenCodeReasoning
Модальности:
Генерация текста
Области применения:
Логика и рассуждение Диалог / чат
Задача: Генерация текста
Автор: nbeerbower
Теги: mistral, orpo, uncensored, reasoning, chain-of-thought, qlora, experimental, conversational
Лайков: 4 | Загрузок: 9
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
