reaperdoesntknow commited on
Commit
6b36dff
·
verified ·
1 Parent(s): dce3a50

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

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -240,7 +240,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
240
 
241
  ## From the Convergent Intelligence Portfolio
242
 
243
- **[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.
244
 
245
  Top model: [Qwen3-1.7B-Coder-Distilled-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT) — 508 downloads
246
 
 
240
 
241
  ## From the Convergent Intelligence Portfolio
242
 
243
+ **[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.
244
 
245
  Top model: [Qwen3-1.7B-Coder-Distilled-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT) — 508 downloads
246