reaperdoesntknow commited on
Commit
a36f04d
·
verified ·
1 Parent(s): b9851e7

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

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -235,7 +235,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
235
 
236
  ## From the Convergent Intelligence Portfolio
237
 
238
- **[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.
239
 
240
  Top model: [Qwen3-1.7B-Coder-Distilled-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT) — 508 downloads
241
 
 
235
 
236
  ## From the Convergent Intelligence Portfolio
237
 
238
+ **[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.
239
 
240
  Top model: [Qwen3-1.7B-Coder-Distilled-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT) — 508 downloads
241