CherryPit-1.2-2B is the third release of CherryPit from DRUPEs (Dense Representation & Unified Parameter Encoding Systems), built on MiniCPM5-2B. It is much better at combining things: web apps that need two, three or four features in one component now pass 1.5x to 4x as often as with CherryPit-1.1, while single features, coding, math and instruction following all went up a little. It also stops dropping its own name into ordinary answers. Same size, architecture and speed as 1.0 and 1.1. Both models were run on the same harness, items, prompts and seeds (bf16 weights in vLLM). We fixed a harness bug (text-path evals were fed two start-of-text tokens), so 1.1’s numbers here are re-measured and differ from its card. — The web-app training used only our own generated tasks, never WebApp1K, so the Duo / Trio / Quartet gains are on a benchmark the model has not seen. — No benchmark got significantly worse: every row was checked per item (paired sign tests) against 1.0 and 1.1. — Composition training: reinforcement learning on generated multi-feature web apps and multi-step code pipelines. — Self-taught rounds: the model trained on its own answers that passed the tests on combined…
Модальности:
Генерация текста
Области применения:
Генерация кода Математика Логика и рассуждение Диалог / чат
Задача: Генерация текста
Автор: DRUPEs
Теги: llama, code, coding, web-development, math, reasoning, tool-calling, on-device
Лайков: 3 | Загрузок: 147
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.