Post
110
BananaMind Daily Digest is back!
🚀 SupraLabs / Supra2.6‑Pico – a brand‑new 2.97 M‑parameter tiny language model
SupraLabs/Supra2.6-Pico
Why it matters: the model packs 2,972,496 unique parameters into an 11.9 MB fp32 weight file, runs with a 1,024‑token context and a 4,096‑token vocabulary. Its hybrid architecture mixes three gated‑delta‑net (GDN‑2) blocks with a gated grouped‑query attention block per group, giving linear‑time recurrence for 6 of 8 layers and global attention for the remaining 2. The design includes learned softmax attention‑residual mixing, RMSNorm, and SwiGLU FFNs (hidden 352). This is a notable step for sub‑3 M models, offering strong efficiency on edge hardware while introducing novel GDN‑2 and gated‑GQA mechanisms.
🤖 BananaMind / BananaMind‑3‑10M‑Training – updated training repo for the 3‑10 M‑parameter series
BananaMind/BananaMind-3-10M-Training
Mid-training checkpoints of BananaMind 3 10M
🧪 BananaMind / 2.5‑pro‑test – community discussion on the BananaMind 2.5 Pro checkpoint
BananaMind/2.5-pro-test
Early feedback thread evaluating performance and potential issues of the 2.5‑pro checkpoint before a formal release.
🌍 Open ASR Leaderboard – Egyptian and Nigerian English added
https://huggingface.co/blog/open-asr-leaderboard-liva
Expands the multilingual ASR benchmark with two new dialects, improving coverage for African English varieties.
📊 AxiomicLabs – Open SLM Leaderboard discussion space
AxiomicLabs/Open_SLM_Leaderboard
Ongoing conversation about ranking small‑language models, inviting submissions and metric proposals.
🪐 NVIDIA Cosmos 3 – Open models for interactive world simulation (article)…
—
🕒 Posted 06 Nov 2026, 18:55 CET. Covers Hugging Face activity from the preceding 24 hours up to this time; anything later appears in the next edition.
🚀 SupraLabs / Supra2.6‑Pico – a brand‑new 2.97 M‑parameter tiny language model
SupraLabs/Supra2.6-Pico
Why it matters: the model packs 2,972,496 unique parameters into an 11.9 MB fp32 weight file, runs with a 1,024‑token context and a 4,096‑token vocabulary. Its hybrid architecture mixes three gated‑delta‑net (GDN‑2) blocks with a gated grouped‑query attention block per group, giving linear‑time recurrence for 6 of 8 layers and global attention for the remaining 2. The design includes learned softmax attention‑residual mixing, RMSNorm, and SwiGLU FFNs (hidden 352). This is a notable step for sub‑3 M models, offering strong efficiency on edge hardware while introducing novel GDN‑2 and gated‑GQA mechanisms.
🤖 BananaMind / BananaMind‑3‑10M‑Training – updated training repo for the 3‑10 M‑parameter series
BananaMind/BananaMind-3-10M-Training
Mid-training checkpoints of BananaMind 3 10M
🧪 BananaMind / 2.5‑pro‑test – community discussion on the BananaMind 2.5 Pro checkpoint
BananaMind/2.5-pro-test
Early feedback thread evaluating performance and potential issues of the 2.5‑pro checkpoint before a formal release.
🌍 Open ASR Leaderboard – Egyptian and Nigerian English added
https://huggingface.co/blog/open-asr-leaderboard-liva
Expands the multilingual ASR benchmark with two new dialects, improving coverage for African English varieties.
📊 AxiomicLabs – Open SLM Leaderboard discussion space
AxiomicLabs/Open_SLM_Leaderboard
Ongoing conversation about ranking small‑language models, inviting submissions and metric proposals.
🪐 NVIDIA Cosmos 3 – Open models for interactive world simulation (article)…
—
🕒 Posted 06 Nov 2026, 18:55 CET. Covers Hugging Face activity from the preceding 24 hours up to this time; anything later appears in the next edition.
