Fine-tuned LoRA on DeepSeek-R1-Distill-Qwen-1.5B for Dyck language completion with step-by-step reasoning. The model completes balanced bracket sequences (Dyck words) and optionally explains its reasoning. — Base model: unsloth/DeepSeek-R1-Distill-Qwen-1.5B — Method: LoRA (r=64, alpha=128), merged and saved as 16-bit — Task: Given a prefix of opening brackets, output the minimal closing brackets to form a valid Dyck sequence; training uses reasoning + final answer format — Bracket pairs: (), [], {}, , ⟨⟩, ⟦⟧, ⦃⦄, ⦅⦆ — Dataset: ~40k Dyck completion examples (user prompt + assistant reasoning + completion) — Epochs: 4 — Effective batch size: 64 (perdevice 16 × gradientaccumulatio Hugging Face’s Inference Providers usually deploy full causal LMs, so they often do not list adapter-only repos. You can still use the model in two ways: 1. Run inference yourself (code below). 2. Deploy a Space using the Gradio app in the project’s space/ folder so the model is usable on HF via the Space. To make the model usable on Hugging Face without relying…
Модальности:
Генерация текста
Области применения:
Логика и рассуждение Диалог / чат
Задача: Генерация текста
Автор: SniperMinion
Теги: qwen2, dyck, formal-language, reasoning, lora, unsloth, conversational, en
Лайков: 3 | Загрузок: 33
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
