This repository is a conversion of XHToken/Spark-X2.6-4B to LiteRT-LM (.litertlm), made with litert-torch 0.9.3 for LiteRT-LM 0.19.0: on a Mac Studio (Apple M4 Max) GPU the int4 file decodes at 91.2 tok/s (1,024-token prompt, 256 generated tokens, 2026-10-31). Spark-X2.6-4B is the SparkLLM Team’s 4.11B-parameter dense decoder, the first model of the Spark-X2.6 series. Its model card says it builds on Spark-X2.5-4B, keeps its architecture and gains its capability from improved post-training. That architecture has 36 layers, hidden size 2560, 16 query and 4 KV heads of 256, three sliding-window (512) layers per full-attention layer, per-head sigmoid gates on the attention output, exact-GELU gated MLPs and a 131,072-entry tied vocabulary. It is a reasoning model: it thinks inside … before it answers. These files carry that: the prompt template opens the thought the way the vendor’s chat template does, and the files declare a thought channel, so LiteRT-LM keeps the reasoning out of the answer. Apache-2.0. All three files declare fp32 GPU activations. The int4 file also uses LiteRT-LM’s GPU composite ops for the KV-cache writes and the attention products, with its weights unchanged…
Модальности:
Генерация текста
Области применения:
Логика и рассуждение
Задача: Генерация текста
Автор: litert-community
Теги: litert-lm, litert, litertlm, on-device, edge, spark, reasoning
Лайков: 3 | Загрузок: 405
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
