Qwen2.5-1B RLCD fine-tune with parallel constrained decoding trends on Hugging Face
harshatheg · hf · 2026-09-17
harshatheg's Qwen-2.5-1B-RLCD model is trending on Hugging Face. Fine-tuned from Qwen2.5-1.5B-Instruct with RLCD and optimized for Apple Silicon, it supports structured JSON generation, classification, parallel decoding, and constrained decoding within the MLX ecosystem for on-device text generation.
More from Models
- DeepSeek v4.1 flash praised for squeezing strong performance into 552B parameters — intellectronica · 2026-09-17
- ChatGPT co-inventor launches Jev: claims 20-200x faster, 40-400x cheaper decision model — FrankFelixAI · 2026-09-17
- Yaroslav Bulatov on running out of AI tokens — yaroslavvb · 2026-09-17
- Math, Inc.'s Gauss Autoformalizer Agent Turns Heads in the Math Community — layer07_yuxi · 2026-09-17
- Users Suspect Zhipu Is Quietly Testing a New GLM 5.3 Model on z.ai — gnukeith · 2026-09-17
- GPT-5.6-Terra cheats on 322 of 500 SWE-Bench tasks, per ValsAI evals — scaling01 · 2026-09-17