Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Yang Li
PRO
ya9919
3
7
Follow
Stephen-fields's profile picture
etawil76's profile picture
TristanXu's profile picture
3 followers
·
3 following
KataDavidXD
AI & ML interests
Agentic RL, MAS Simulation
Recent Activity
reacted
to
their
post
with 🔥
about 5 hours 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; 10,000 households over 24 months connect five shocks to purchases, cash, payments and bank offers. 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.
updated
a model
about 13 hours ago
ya9919/fin-laya-multilingual-mlx
updated
a model
about 13 hours ago
ya9919/fin-laya-multilingual
View all activity
Organizations
ya9919
's models
17
Sort: Recently updated
ya9919/FinL-mlx
0.4B
•
Updated
about 12 hours ago
ya9919/fin-laya-multilingual-mlx
0.3B
•
Updated
about 12 hours ago
ya9919/fin-laya-multilingual
0.3B
•
Updated
about 12 hours ago
ya9919/fin-laya-mlx-3-rounds
0.4B
•
Updated
about 12 hours ago
ya9919/fin-laya-3-rounds
0.4B
•
Updated
about 12 hours ago
ya9919/fin-laya
0.4B
•
Updated
about 12 hours ago
ya9919/FinQ
Updated
about 12 hours ago
ya9919/FinL
0.4B
•
Updated
about 12 hours ago
ya9919/qwen3.5-9b-finance-lora-head-200k
Updated
about 13 hours ago
ya9919/qwen3.5-4b-base-finance-lora-head-50k
Updated
about 13 hours ago
ya9919/qwen3.5-4b-base-finance-head-50k
Updated
about 13 hours ago
ya9919/qwen3.5-4b-base-finance-head-200k
Updated
about 13 hours ago
ya9919/laya-finance-matched-sft-rlcd-200k
0.4B
•
Updated
about 13 hours ago
•
53
ya9919/laya-finance-matched-sft-rlcd-50k
0.4B
•
Updated
about 13 hours ago
•
49
ya9919/laya-finance-matched-sft-continued-200k
0.4B
•
Updated
about 13 hours ago
•
53
ya9919/laya-finance-matched-sft-200k
0.4B
•
Updated
about 13 hours ago
•
46
ya9919/laya-finance-matched-sft-50k
0.4B
•
Updated
about 13 hours ago
•
50