-
el4/Xenon-26B-A4B-OPAL-GGUF
Text Generation ⢠25B ⢠Updated ⢠64 ⢠2 -
el4/Qwopus3.6-35B-A3B-Coder-OPAL-GGUF
Text Generation ⢠36B ⢠Updated ⢠15.3k ⢠4 -
el4/Darwin-36B-Opus-OPAL-GGUF
Text Generation ⢠35B ⢠Updated ⢠11.9k ⢠11 -
el4/SIQ-1-35B-OPAL-GGUF
Text Generation ⢠35B ⢠Updated ⢠16.5k ⢠1
š¦ dancing crab
Damien
el4
AI & ML interests
I do anything really | #quantwizard | ETH: 0xDEE7fa8C421BD038D32e4441ea1aDe72fE973706
Recent Activity
liked a Space about 7 hours ago
FINAL-Bench/model-galaxy reacted to SeaWolf-AI's post with š„ 1 day 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 ā 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:
š Rebuild it from scratch, or fork the recipe for your own model
š¬ Study a real heterogeneous-attention MoE ā 49 layers place 5 attention mechanisms on a 7Ć7 Latin square, arranged as a clean, attributable ablation
š Trace training dynamics across the released checkpoints (110k / 115k / 162k)
It's a modest 6.59B model, and an honest one ā 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. š¤
š Full write-up ā
[blog] Ā· https://huggingface.co/blog/FINAL-Bench/opensource-llm
š¦ 5 Attention Base Ā· https://huggingface.co/FINAL-Bench/Aether-7B-5Attn
šÆ 5 Attention Instruct Ā· https://huggingface.co/FINAL-Bench/Aether-7B-5Attn-it
š 5 Attention Live demo Ā· https://huggingface.co/spaces/FINAL-Bench/Aether-Sovereign-AI
š¦ 7 Attention Base Ā· https://huggingface.co/FINAL-Bench/Aether-7B-7Attn-base
š¦ 11 Attention Base Ā· https://huggingface.co/FINAL-Bench/Aether-6B-11Attn-base
𧬠Collection · https://huggingface.co/collections/FINAL-Bench/aether-foundation-model
#opensource #LLM #MoE #reproducibility #Apache2Organizations
None yet