!Moon-pie Rescue. An ivory cat catches a pumpkin pie on a cratered moon while red and gold maple leaves drift across a starry sky. Moon-beam is a mixture-of-experts model with 8B total parameters, about 1B active per token, and a 131,072-token context window. It pairs inclusionAI’s Ling-3.0-tiny with Tablinum’s searchable knowledge library, the engram. Round 1b was fine-tuned with QLoRA on retrieved passages, math problems, tool calls, and multi-turn conversations. Model and evaluation notes On the model-card protocol evaluation (temperature 1.0, topp 0.95, topk 20, up to 32K new tokens, the full 131K window), Moon-beam scored 95.5% on 400 GSM8K questions with thinking on. On EngramBench it answered 436 of 503 questions correctly (86.5%) with thinking on and passages from each question’s own table. As a support agent on tau2-bench it earned an average reward of 0.71 on airline and 0.80 on retail conversations. > Preview. These weights are the release candidate (round 1b). They run today with the Tablinum-2 library. Tablinum-3, about twice the library, is still being built and tested; when it is, these cards and the engram pack will be updated and the -Preview suffix dropped.…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: tablinum
Теги: gguf, tablinum, engram, moon-beam, ling, moe, thinking, tool-calling
Лайков: 3 | Загрузок: 461
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
