LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning. — Best-in-class performance: A 1.2B model rivaling much larger models, bringing high-quality AI to your pocket. — Fast edge inference: 239 tok/s decode on AMD CPU, 82 tok/s on mobile NPU. Runs under 1GB of memory with day-one support for llama.cpp, MLX, and vLLM. — Scaled training: Extended pre-training from 10T to 28T tokens and large-scale multi-stage reinforcement learning. LFM2.5-1.2B-Instruct is a general-purpose text-only model with the following features: — Number of parameters: 1.17B — Number of layers: 16 (10 double-gated LIV convolution blocks + 6 GQA blocks) — Training budget: 28T tokens — Context length: 32,768 tokens — Vocabulary size: 65,536 — Languages: English, Arabic, Chinese, French, German, Japanese, Korean, Spanish — Generation parameters: — temperature: 0.1 — topk: 50 — topp: 0.1 — repetitionpenalty: 1.05` We recommend using it It is not recommended for knowledge-intensive tasks and programming. LFM2.5 uses a ChatML-like format. See the Chat Template…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: FastFlowLM
Теги: lfm2, liquid, lfm2.5, edge, conversational, en, ar, zh
Лайков: 3 | Загрузок: 232
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
