hugpadhugpad

Efficient-Large-Model / Fast_dLLM_v2_1.5B

Other1.5B2.2K15Updated Jan 22, 2026
Hugging Face

Downloads

2.2K

Likes

15

Last updated

Jan 22, 2026

License

apache-2.0

Autoregressive (AR) large language models (LLMs) have achieved remarkable performance across a wide range of natural language tasks, yet their inherent sequential decoding limits inference efficiency.

Tags

  • Fast_dLLM_Qwen
  • custom_code
  • en

Technical specifications

Parameters1.5B
LibraryNot available
Languagesen
Base modelQwen/Qwen2.5-1.5B-Instruct
Licenseapache-2.0