Gguf version. 3.91B parameters, 2 experts active, 4 in total. This is the non-experimental version of Superthoughts Lite v2. Offering better accuracy at all tasks, better performance and less looping while generating responses. We trained it by first creating a base model for all the experts, which was fine-tuned using GRPO techniques using Unsloth on top of meta-llama/Llama-3.2-1B-Instruct. After making the base model, we trained each potential expert using SFT. After doing SFT, we did GRPO again. in total there are 4 experts: — Chat reasoning expert, — Math reasoning expert, — Code reasoning expert, — Science reasoning expert. By doing this, we obtained a powerful, lite reasoning model that is very usable for its size. This model is a direct replacement of Pinkstack/Superthoughts-lite-v1. Pinkstack/Superthoughts-lite-v1 was not able to generate code, and had very poor text performance. V2 is much more usable. The model can generate up to 16,380 tokens and has a context size of 131072 It has been fine tuned to generated thinking data in-between xml tags. note that it may still have some slight looping but they are rare. While some safety alignment was done by us, it was very…
Модальности:
Генерация текста
Области применения:
Генерация кода Математика Диалог / чат Химия
Задача: Генерация текста
Автор: Pinkstack
Теги: gguf, chemistry, code, math, grpo, conversational, moe, en
Лайков: 4 | Загрузок: 41
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
