Hugging Face's logo
Dominic Nidy's picture

Dominic Nidy

domnidy
2 15
Gargaz's profile picture Mi6paulino's profile picture
Β·

AI & ML interests

None yet

Recent Activity

reacted to SeaWolf-AI's post with ❀️ 11 days ago
A small gift for anyone building or studying foundation models. Most "open" models hand you the weights and stop there. With Aether-7B-5Attn we wanted to hand over the whole thing β€” so you can actually learn from it, reproduce it, and build on it: the data recipe, the training code, every hyperparameter, the complete logs, and the intermediate checkpoints. All Apache-2.0, reproducible byte-for-byte. What you can do with it: πŸ” Rebuild it from scratch, or fork the recipe for your own model πŸ”¬ Study a real heterogeneous-attention MoE β€” 49 layers place 5 attention mechanisms on a 7Γ—7 Latin square, arranged as a clean, attributable ablation πŸ“ˆ Trace training dynamics across the released checkpoints (110k / 115k / 162k) It's a modest 6.59B model, and an honest one β€” the limitations (no KV-cache in this build, small scale) are written right in the card. We're not claiming it's special. If any piece of it saves you time or teaches you something, that's exactly what we hoped for. πŸ€— πŸ“– Full write-up β†’ [blog] Β· https://huggingface.co/blog/FINAL-Bench/opensource-llm πŸ“¦ 5 Attention Base Β· https://huggingface.co/FINAL-Bench/Aether-7B-5Attn 🎯 5 Attention Instruct Β· https://huggingface.co/FINAL-Bench/Aether-7B-5Attn-it πŸš€ 5 Attention Live demo Β· https://huggingface.co/spaces/FINAL-Bench/Aether-Sovereign-AI πŸ“¦ 7 Attention Base Β· https://huggingface.co/FINAL-Bench/Aether-7B-7Attn-base πŸ“¦ 11 Attention Base Β· https://huggingface.co/FINAL-Bench/Aether-6B-11Attn-base 🧬 Collection Β· https://huggingface.co/collections/FINAL-Bench/aether-foundation-model #opensource #LLM #MoE #reproducibility #Apache2
liked a model 12 days ago
facebook/dinov3-vitl16-pretrain-lvd1689m
upvoted a paper 5 months ago
MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants
View all activity

Organizations

None yet