The second generation of the MicroLlama series. This is an ultra-compact, 45-million parameter language model trained from scratch and fine-tuned using Supervised Fine-Tuning (SFT) on the clean Alpaca dataset. — Size: ~45M parameters — runs lightning-fast even on a potato. — Vocabulary: Custom LLaMA-based tokenizer. — Grammar Over Mind: Thanks to SFT, the model has pristine English grammar and strict formatting, though its world-knowledge is hilariously limited by its scale. — Lore: Has a strange obsession with cats, parks, and existential AI humor. «`python from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.frompretrained(«ViorikaAI-org/MicroLlama-v2») model = AutoModelForCausalLM.frompretrained(«ViorikaAI-org/MicroLlama-v2») prompt = «user: How are you?nassistant: » inputs = tokenizer(prompt, returntensors=»pt») outputs = model.generate(inputs, maxnewtokens=50) print(tokenizer.decode(outputs[0]))
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: ViorikaAI-org
Теги: llama, tiny-lm, conversational, en, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 25
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
