tsfrm/cheese-3b - Каталог нейросетей
Генерация текста

tsfrm/cheese-3b

Добавлено:
tsfrm/cheese-3b

Llama 3.2 3B Instruct turned into a cheese pun machine. Input a phrase, get the phrase cheesed back. Fine-tunes that answer questions are a solved problem. I wanted one that warps whatever you type. The whole thing trains on a laptop in an afternoon, which felt like a decent demo of how far a small LoRA run can push behavior takeover on a narrow task. The interesting part was round 3. After two rounds the model handled idiom-shaped input fine but echoed anything without an obvious pun word («the quick brown fox jumps over the lazy dog» came back unchanged). Adding 262 hand-written transformations of arbitrary text fixed it — «quiche brown fox», «cheddar-ing today». Echo fallback didn’t come back. — Sometimes appends chatty filler after the pun instead of stopping («netflix and chill, wine and cheese for two» — acceptable, but not what I asked for). — Substitution quality varies: tight phonetic swaps (be→brie, good→gouda) are the norm, but it occasionally reaches for a stretchy swap (odds→goudas) when nothing phonetic is available. — Prompts with zero dairy potential mostly still transform now, though quality there is more hit-and-miss than on idioms. Trained for fun on personal…

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: tsfrm
Теги: mlx, llama, lora, fine-tune, conversational, 4-bit
Лайков: 3  |  Загрузок: 53

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.