Stateful Language Models, Supervised Finetuned from Qwen3
xyliu
xiaoyuanliu
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
SkillNet: Create, Evaluate, and Connect AI Skills updated
a model about 1 month ago
xiaoyuanliu/StateLM-14B-RL-0124-CKPT32 published
a model about 1 month ago
xiaoyuanliu/StateLM-14B-RL-0124-CKPT32 Organizations
None yet
HELMET-Eval
21 subsets of HELMET evaluation datasets
-
xiaoyuanliu/HELMET_icl_nlu_8296shot_balance__eval
Viewer • Updated • 500 • 6 -
xiaoyuanliu/HELMET_icl_banking77_5900shot_balance__eval
Viewer • Updated • 500 • 6 -
xiaoyuanliu/HELMET_icl_trec_fine_6400shot_balance__eval
Viewer • Updated • 500 • 6 -
xiaoyuanliu/HELMET_icl_trec_coarse_6600shot_balance__eval
Viewer • Updated • 500 • 6
StateLM
Stateful Language Models, Supervised Finetuned from Qwen3
HELMET-Eval
21 subsets of HELMET evaluation datasets
-
xiaoyuanliu/HELMET_icl_nlu_8296shot_balance__eval
Viewer • Updated • 500 • 6 -
xiaoyuanliu/HELMET_icl_banking77_5900shot_balance__eval
Viewer • Updated • 500 • 6 -
xiaoyuanliu/HELMET_icl_trec_fine_6400shot_balance__eval
Viewer • Updated • 500 • 6 -
xiaoyuanliu/HELMET_icl_trec_coarse_6600shot_balance__eval
Viewer • Updated • 500 • 6
models 90
xiaoyuanliu/StateLM-14B-RL-0124-CKPT32
Text Generation • 15B • Updated
• 3
xiaoyuanliu/StateLM-8B-RL-0123-CKPT32
Text Generation • 8B • Updated
• 3
xiaoyuanliu/StateLM-4B-SFT
Text Generation • 4B • Updated
xiaoyuanliu/StateLM-14B-SFT
Text Generation • 15B • Updated
xiaoyuanliu/StateLM-8B-SFT
Text Generation • 8B • Updated
xiaoyuanliu/Qwen3-30B-A3B-SFT-V4_OPT
Text Generation • 31B • Updated
xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo-verifier
Text Generation • 2B • Updated
xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-verifier
Text Generation • 3B • Updated
xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-verifier
Text Generation • 8B • Updated
xiaoyuanliu/Qwen3-4B-SFT-V2.1-ml.16K-lr.1e-5-ep.3
Text Generation • 4B • Updated
datasets 71
xiaoyuanliu/mmlu-redux
Viewer
• Updated
• 3k • 8
xiaoyuanliu/LongBench-v2-verified
Viewer
• Updated
• 503 • 7
xiaoyuanliu/claude4-agentic-samples-V4-opt-swift-format-500
Viewer
• Updated
• 500 • 7
xiaoyuanliu/claude4-agentic-samples-V4-opt-swift-format
Viewer
• Updated
• 35.7k • 11
xiaoyuanliu/V4-BAScan-Warmup360
Viewer
• Updated
• 7.17k • 11
xiaoyuanliu/longmemeval-s
Viewer
• Updated
• 500 • 7
xiaoyuanliu/LongBench-v2-rlvr
Viewer
• Updated
• 503 • 12
xiaoyuanliu/LongBench-v2-T100
Viewer
• Updated
• 100 • 9
xiaoyuanliu/V4-BA-Warmup300
Viewer
• Updated
• 3.72k • 8
xiaoyuanliu/claude4-agentic-samples-V4-Balanced
Viewer
• Updated
• 28.6k • 10