Hugging Face's logo
TaeHyun Kim's picture
6 62

TaeHyun Kim

Ctulu82
ausntmarzi's profile picture Mylove007's profile picture solarbeams's profile picture
Ā·

AI & ML interests

None yet

Recent Activity

reacted to SeaWolf-AI's post with šŸ¤— 5 days ago
šŸ§¬ Darwin-27B-Opus: 86.9% on GPQA Diamond ā€” World #5, Zero Training We are excited to share Darwin-27B-Opus, a 27B model that achieved 86.9% on GPQA Diamond ā€” ranking #5 globally on the HuggingFace leaderboard ā€” without a single gradient update. How? Darwin breeds pretrained models through evolutionary FFN crossbreeding. The father (Qwen3.5-27B) provides the reasoning architecture; the mother (Claude 4.6 Opus Reasoning Distilled) contributes structured chain-of-thought knowledge. CMA-ES automatically discovers optimal per-layer blending ratios ā€” no human tuning required. The result surpasses the original Qwen3.5-27B (85.5%), GLM-5.1 (744B, 86.2%), and Qwen3.5-122B (86.6%). A 27B model outperforming 744B ā€” with zero training, zero data, one GPU, ~2 hours. We also confirmed hybrid vigor on Korean benchmarks: Darwin-27B-KR (2nd generation offspring) surpassed both parents on CLIcK, winning 7 out of 11 categories. The evolutionary optimizer independently assigned 93% of FFN from the Korean-specialized mother while preserving 93% of attention from the reasoning-specialized father ā€” autonomously validating our core principle: FFN carries knowledge, Attention carries reasoning. šŸ“Š Public release: 10 days ā†’ 300+ community derivatives, 120K+ downloads. šŸ”— Links: Darwin-27B-Opus: https://huggingface.co/FINAL-Bench/Darwin-27B-Opus article: https://huggingface.co/blog/FINAL-Bench/darwin-gpqa Darwin Family Collection: https://huggingface.co/collections/FINAL-Bench/darwin-family If foundation models are raw ore, Darwin is the forge. We are just getting started. šŸ”„
reacted to SeaWolf-AI's post with šŸ§  5 days ago
šŸ§¬ Darwin-27B-Opus: 86.9% on GPQA Diamond ā€” World #5, Zero Training We are excited to share Darwin-27B-Opus, a 27B model that achieved 86.9% on GPQA Diamond ā€” ranking #5 globally on the HuggingFace leaderboard ā€” without a single gradient update. How? Darwin breeds pretrained models through evolutionary FFN crossbreeding. The father (Qwen3.5-27B) provides the reasoning architecture; the mother (Claude 4.6 Opus Reasoning Distilled) contributes structured chain-of-thought knowledge. CMA-ES automatically discovers optimal per-layer blending ratios ā€” no human tuning required. The result surpasses the original Qwen3.5-27B (85.5%), GLM-5.1 (744B, 86.2%), and Qwen3.5-122B (86.6%). A 27B model outperforming 744B ā€” with zero training, zero data, one GPU, ~2 hours. We also confirmed hybrid vigor on Korean benchmarks: Darwin-27B-KR (2nd generation offspring) surpassed both parents on CLIcK, winning 7 out of 11 categories. The evolutionary optimizer independently assigned 93% of FFN from the Korean-specialized mother while preserving 93% of attention from the reasoning-specialized father ā€” autonomously validating our core principle: FFN carries knowledge, Attention carries reasoning. šŸ“Š Public release: 10 days ā†’ 300+ community derivatives, 120K+ downloads. šŸ”— Links: Darwin-27B-Opus: https://huggingface.co/FINAL-Bench/Darwin-27B-Opus article: https://huggingface.co/blog/FINAL-Bench/darwin-gpqa Darwin Family Collection: https://huggingface.co/collections/FINAL-Bench/darwin-family If foundation models are raw ore, Darwin is the forge. We are just getting started. šŸ”„
reacted to SeaWolf-AI's post with šŸ¤Æ 5 days ago
šŸ§¬ Darwin-27B-Opus: 86.9% on GPQA Diamond ā€” World #5, Zero Training We are excited to share Darwin-27B-Opus, a 27B model that achieved 86.9% on GPQA Diamond ā€” ranking #5 globally on the HuggingFace leaderboard ā€” without a single gradient update. How? Darwin breeds pretrained models through evolutionary FFN crossbreeding. The father (Qwen3.5-27B) provides the reasoning architecture; the mother (Claude 4.6 Opus Reasoning Distilled) contributes structured chain-of-thought knowledge. CMA-ES automatically discovers optimal per-layer blending ratios ā€” no human tuning required. The result surpasses the original Qwen3.5-27B (85.5%), GLM-5.1 (744B, 86.2%), and Qwen3.5-122B (86.6%). A 27B model outperforming 744B ā€” with zero training, zero data, one GPU, ~2 hours. We also confirmed hybrid vigor on Korean benchmarks: Darwin-27B-KR (2nd generation offspring) surpassed both parents on CLIcK, winning 7 out of 11 categories. The evolutionary optimizer independently assigned 93% of FFN from the Korean-specialized mother while preserving 93% of attention from the reasoning-specialized father ā€” autonomously validating our core principle: FFN carries knowledge, Attention carries reasoning. šŸ“Š Public release: 10 days ā†’ 300+ community derivatives, 120K+ downloads. šŸ”— Links: Darwin-27B-Opus: https://huggingface.co/FINAL-Bench/Darwin-27B-Opus article: https://huggingface.co/blog/FINAL-Bench/darwin-gpqa Darwin Family Collection: https://huggingface.co/collections/FINAL-Bench/darwin-family If foundation models are raw ore, Darwin is the forge. We are just getting started. šŸ”„
View all activity

Organizations

OpenFree_AI's profile picture