Ling-3.0-tiny-UBTree released
The story so far
inclusionAI has released a fine-tuned model Ling-3.0-tiny-UBTree-B16 based on UBTree technology, with 183.1M parameters, combining a five-layer DFlash backbone and a bigram selector, achieving 2.6-3.5 times speed improvement on benchmarks like GSM8K and MATH-500. This model needs to be used in conjunction with the target model. The UBTree adaptation for the open-source version of SGLang has not yet been released.
AI-written from the reports · Updated 27 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Ant Group inclusionAI · Hugging Face new modelsinclusionAI/Ling-3.0-tiny-UBTree
inclusionAI released the UBTree fine-tuned version of Ling-3.0-tiny, Ling-3.0-tiny-UBTree-B16, with 183.1M parameters, combining a five-layer DFlash backbone and a bigram selector, achieving 2.6-3.5 times speed improvement on benchmarks like GSM8K and MATH-500. This model needs to be used in conjunction with the target model. The UBTree adaptation for the open-source version of SGLang has not yet been released.