Hugging Face's logo
melison's picture
👋 Open to Work

melison

animemory
9 5 219
littlebird13's profile picture xiao2mo's profile picture 21world's profile picture
·

AI & ML interests

None yet

Recent Activity

liked a dataset 3 days ago
MaxRondelli/BlenderRAG
liked a model 4 days ago
DiscoSea/vmr3D
reacted to ya9919's post with 🔥 5 days ago
S²-MAS: 500M household personas • 2,925,263 post-training examples • 12M distinct model-inferred agents / 24M choices. Main policies: FinQ (4B LoRA + head, 200k) and FinL (421M Laya, six rounds). FinL-mlx is the MLX version. English FinL-mlx (six-round FP16): 74.5544% accuracy / 38.3746% question-macro F1. FinL-bilingual-mlx: 9.10 ms latency; 22.72× Jev 1.13 API throughput / 2.42× the same checkpoint in PyTorch. FinL has the largest domain post-training set among the paper's financial decision models with disclosed scales: 2,925,263 examples. 12M distinct synthetic households form the largest directly model-evaluated population among the compared LLM-inference workloads. 24M choices + 288M monthly ledger states in 3h59m17s on 14 GPUs (8 H100 + 6 A100). Test: 240,458 records / 119 question versions. Timing: 3 Chinese inputs, 60 calls/arm, batch/concurrency 1, one A100 40GB; API round trip included. 6 routes: Encoder option scoring; LM + learned decision head; Next-token decision SFT; Dynamic schema classification; Multimodal encoder decisions; Provider decision interfaces. 10 development-selected trained variants: Native: SFT50; SFT200; SFT50→RLCD+50k; SFT200→RLCD+200k; SFT200→CE+200k. Qwen: 4B Head50; 4B Head200; 4B LoRA50; FinQ (4B LoRA200); 9B LoRA200. 12 benchmarked models/systems; 17 repository entries, including 2 documentation-only three-round entries. 8 financial tasks. Independent synthetic companion: 2M states + 32k unlabeled inputs. Blog: https://huggingface.co/blog/ya9919/s2-mas Paper: https://github.com/KataDavidXD/s2-mas/blob/main/paper/S2_MAS_Paper.pdf Scientific scripts: https://github.com/KataDavidXD/s2-mas Models: https://huggingface.co/collections/ya9919/s-mas-models-finq-and-finl Datasets: https://huggingface.co/collections/ya9919/s-mas-dataset-resources GENESE engine remains private. Component research terms apply; Wikidata CC0.
View all activity

Organizations

anime fans community's profile picture anime empire's profile picture