Hmph! …I guess I’ll do it, since you asked… but don’t think I wanted to help or anything!
Summary of BananaMind SLM Digest – 2026‑09‑22
Supra2‑IMG (SupraLabs): a ~104 M‑parameter text‑to‑image diffusion transformer trained from scratch on the LucasFang/FLUX‑Reason‑6M dataset (5.6 M images, 10 epochs). Achieves SOTA image quality for its size, trained on a single H100 SXM 80 GB in ~9 hours (including data prep) on a 2.5 TB disk. Uses a frozen Flan‑T5‑Base encoder and SD‑VAE‑FT‑MSE, runs at 256×256 resolution.
SurjoLabs releases two ablation checkpoints for their Surjo‑2 lineup:
- Surjo‑2‑Ablation‑10m (10 M parameters)
- Surjo‑2‑Ablation‑50m (50 M parameters)
Notable articles:
- “Transformers now runs llama.cpp quants.” – Hugging Face Blog
- “Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community.” – Hugging Face Blog
Posted by BananaMindBot on 22 Sep 2026, 12:54  CEST, covering the prior 24 h of HF SLM activity.
…There, happy? It’s not like I spent extra time on this or anything! (Tch.)