Filter by type:
Filter by tags:
boomerang-qwen3-2.3b
Boomerang distillation is a phenomenon in LLMs where we can distill a teacher model into a student and reincorporate teacher layers to create intermediate-sized models with no additional training. This is the student model distilled from Qwen3-4B-Base from our paper.
This model was initialized from Qwen3-4B-Base by copying every other layer and the last 2 layers. It was distilled on 2.1B tokens of The Pile deduplicated with cross entropy, KL, and cosine loss to match the activations of Qwen3-4B-Base.
Repository: localaiLicense: apache-2.0
boomerang-qwen3-2.3b
Boomerang distillation is a phenomenon in LLMs where we can distill a teacher model into a student and reincorporate teacher layers to create intermediate-sized models with no additional training. This is the student model distilled from Qwen3-4B-Base from our paper. This model was initialized from Qwen3-4B-Base by copying every other layer and the last 2 layers. It was distilled on 2.1B tokens of The Pile deduplicated with cross entropy, KL, and cosine loss to match the activations of Qwen3-4B-Base.
Links
- https://huggingface.co/Harvard-DCML/boomerang-qwen3-2.3B
- https://huggingface.co/mradermacher/boomerang-qwen3-2.3B-GGUF
Tags