dipankarsarkar/grite-corpus
Viewer • Updated • 1.4k • 170
Dipankar Sarkar PRO
dipankarsarkar
AI & ML interests
Building the AI-native stack. Agents as infrastructure, safety as architecture, performance as plumbing. I publish the receipts: papers, datasets, demos.
Recent Activity
liked a model 11 minutes ago
FINAL-Bench/Aether-7B-5Attn reacted to SeaWolf-AI's post with 🤗 11 minutes 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 — 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:
🔁 Rebuild it from scratch, or fork the recipe for your own model
🔬 Study a real heterogeneous-attention MoE — 49 layers place 5 attention mechanisms on a 7×7 Latin square, arranged as a clean, attributable ablation
📈 Trace training dynamics across the released checkpoints (110k / 115k / 162k)
It's a modest 6.59B model, and an honest one — 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. 🤗
📖 Full write-up →
[blog] · https://huggingface.co/blog/FINAL-Bench/opensource-llm
📦 Base · https://huggingface.co/FINAL-Bench/Aether-7B-5Attn
🎯 Instruct · https://huggingface.co/FINAL-Bench/Aether-7B-5Attn-it
🚀 Live demo · https://huggingface.co/spaces/FINAL-Bench/Aether-Sovereign-AI
🧬 Collection · https://huggingface.co/collections/FINAL-Bench/aether-foundation-model
#opensource #LLM #MoE #reproducibility #Apache2 repliedto SeaWolf-AI's post 12 minutes 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 — 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:
🔁 Rebuild it from scratch, or fork the recipe for your own model
🔬 Study a real heterogeneous-attention MoE — 49 layers place 5 attention mechanisms on a 7×7 Latin square, arranged as a clean, attributable ablation
📈 Trace training dynamics across the released checkpoints (110k / 115k / 162k)
It's a modest 6.59B model, and an honest one — 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. 🤗
📖 Full write-up →
[blog] · https://huggingface.co/blog/FINAL-Bench/opensource-llm
📦 Base · https://huggingface.co/FINAL-Bench/Aether-7B-5Attn
🎯 Instruct · https://huggingface.co/FINAL-Bench/Aether-7B-5Attn-it
🚀 Live demo · https://huggingface.co/spaces/FINAL-Bench/Aether-Sovereign-AI
🧬 Collection · https://huggingface.co/collections/FINAL-Bench/aether-foundation-model
#opensource #LLM #MoE #reproducibility #Apache2Organizations
