Hugging Face's logo
Jinki Jeong's picture
8 20

Jinki Jeong

Anserwise
webxos's profile picture SeaWolf-AI's profile picture mayafree's profile picture
Β·

AI & ML interests

None yet

Recent Activity

liked a model about 13 hours ago
FINAL-Bench/Darwin-35B-A3B-Opus-Q8-GGUF
reacted to SeaWolf-AI's post with πŸ€— 1 day ago
🧬 Darwin-35B-A3B-Opus β€” The Child That Surpassed Both Parents What if a merged model could beat both its parents? We proved it can. Darwin-35B-A3B-Opus is a 35B MoE model (3B active) built with our Darwin V5 engine β€” the first evolution system that CT-scans parent models before merging them. πŸ€— Model: https://huggingface.co/FINAL-Bench/Darwin-35B-A3B-Opus The result speaks for itself: GPQA Diamond 90.0%, versus Father (Qwen3.5-35B-A3B) at 84.2% and Mother (Claude 4.6 Opus Distilled) at 85.0%. That's +6.9% over Father and +5.9% over Mother. Not a tradeoff β€” a genuine leap. Meanwhile, MMMLU sits at 85.0% (Father: 85.2%), multimodal is fully intact, and all 201 languages are preserved. How? Model MRI changed everything. Traditional merging is guesswork. Darwin V4 added evolution. Darwin V5 added X-ray vision. Model MRI scans each parent layer by layer and discovers: Mother's L34–L38 is the reasoning engine (peak cosine distance), 50–65% of Mother's experts are dead (killed by text-only distillation), and Father is a healthy generalist with every expert alive. The prescription: transplant Mother's reasoning brain at L38 (90% weight), replace her dead experts with Father's living ones, and let Father's router handle the output layer. Reasoning went up. Versatility stayed intact. No tradeoff β€” just evolution. 35B total, 3B active (MoE) Β· GPQA Diamond 90.0% Β· MMMLU 85.0% (201 languages) Β· Multimodal Image & Video Β· 262K native context Β· 147.8 tok/s on H100 Β· Runs on a single RTX 4090 (Q4) Β· Apache 2.0 Darwin V5's full algorithm and technical details will be released alongside an upcoming paper. πŸš€ Live Demo: https://huggingface.co/spaces/FINAL-Bench/Darwin-35B-A3B-Opus πŸ† FINAL Bench Leaderboard: https://huggingface.co/spaces/FINAL-Bench/Leaderboard πŸ“Š ALL Bench Leaderboard: https://huggingface.co/spaces/FINAL-Bench/all-bench-leaderboard Built by VIDRAFT Β· Supported by the Korean Government GPU Support Program
reacted to SeaWolf-AI's post with πŸ‘ 1 day ago
🧬 Darwin-35B-A3B-Opus β€” The Child That Surpassed Both Parents What if a merged model could beat both its parents? We proved it can. Darwin-35B-A3B-Opus is a 35B MoE model (3B active) built with our Darwin V5 engine β€” the first evolution system that CT-scans parent models before merging them. πŸ€— Model: https://huggingface.co/FINAL-Bench/Darwin-35B-A3B-Opus The result speaks for itself: GPQA Diamond 90.0%, versus Father (Qwen3.5-35B-A3B) at 84.2% and Mother (Claude 4.6 Opus Distilled) at 85.0%. That's +6.9% over Father and +5.9% over Mother. Not a tradeoff β€” a genuine leap. Meanwhile, MMMLU sits at 85.0% (Father: 85.2%), multimodal is fully intact, and all 201 languages are preserved. How? Model MRI changed everything. Traditional merging is guesswork. Darwin V4 added evolution. Darwin V5 added X-ray vision. Model MRI scans each parent layer by layer and discovers: Mother's L34–L38 is the reasoning engine (peak cosine distance), 50–65% of Mother's experts are dead (killed by text-only distillation), and Father is a healthy generalist with every expert alive. The prescription: transplant Mother's reasoning brain at L38 (90% weight), replace her dead experts with Father's living ones, and let Father's router handle the output layer. Reasoning went up. Versatility stayed intact. No tradeoff β€” just evolution. 35B total, 3B active (MoE) Β· GPQA Diamond 90.0% Β· MMMLU 85.0% (201 languages) Β· Multimodal Image & Video Β· 262K native context Β· 147.8 tok/s on H100 Β· Runs on a single RTX 4090 (Q4) Β· Apache 2.0 Darwin V5's full algorithm and technical details will be released alongside an upcoming paper. πŸš€ Live Demo: https://huggingface.co/spaces/FINAL-Bench/Darwin-35B-A3B-Opus πŸ† FINAL Bench Leaderboard: https://huggingface.co/spaces/FINAL-Bench/Leaderboard πŸ“Š ALL Bench Leaderboard: https://huggingface.co/spaces/FINAL-Bench/all-bench-leaderboard Built by VIDRAFT Β· Supported by the Korean Government GPU Support Program
View all activity

Organizations

None yet