reaperdoesntknow commited on
Commit
d8a0ab8
·
verified ·
1 Parent(s): 0ffaa55

Cross-link: DistilQwen collection spotlight — 2026-03-29

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -277,7 +277,7 @@ Built with 🤗 Transformers and a metric-first rethinking of attention. BlackHo
277
 
278
  ## From the Convergent Intelligence Portfolio
279
 
280
- **[DistilQwen Collection](https://huggingface.co/collections/reaperdoesntknow/distilqwen-69bf40ec669117e3f069ef1c)** — Proof-weighted distillation from Qwen3-30B-A3B → 1.7B and 0.6B. Three teacher variants (Instruct, Thinking, Coder), nine models, 2,788 combined downloads. Structure beats scale.
281
 
282
  Top model: [Qwen3-1.7B-Coder-Distilled-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT) — 508 downloads
283
 
 
277
 
278
  ## From the Convergent Intelligence Portfolio
279
 
280
+ **[DistilQwen Collection](https://huggingface.co/collections/reaperdoesntknow/distilqwen-69bf40ec669117e3f069ef1c)** — Our only BF16 series. Proof-weighted distillation from Qwen3-30B-A3B → 1.7B and 0.6B on H100. Three teacher variants (Instruct, Thinking, Coder), nine models, 2,788 combined downloads. The rest of the portfolio proves structure beats scale on CPU. This collection shows what happens when you give the methodology real hardware.
281
 
282
  Top model: [Qwen3-1.7B-Coder-Distilled-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT) — 508 downloads
283