Stateful Language Models, Supervised Finetuned from Qwen3
xyliu
xiaoyuanliu
AI & ML interests
None yet
Recent Activity
upvoted a paper 6 days ago
TraceForge: Distilling with Your Own Thinking liked a model 5 months ago
libertywing/FlashMemory-Deepseek-V4 upvoted a paper 5 months ago
FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse AttentionOrganizations
None yet
21 subsets of HELMET evaluation datasets
-
xiaoyuanliu/HELMET_icl_nlu_8296shot_balance__eval
Viewer • Updated • 500 • 16 -
xiaoyuanliu/HELMET_icl_banking77_5900shot_balance__eval
Viewer • Updated • 500 • 12 -
xiaoyuanliu/HELMET_icl_trec_fine_6400shot_balance__eval
Viewer • Updated • 500 • 13 -
xiaoyuanliu/HELMET_icl_trec_coarse_6600shot_balance__eval
Viewer • Updated • 500 • 17
Stateful Language Models, Supervised Finetuned from Qwen3
21 subsets of HELMET evaluation datasets
-
xiaoyuanliu/HELMET_icl_nlu_8296shot_balance__eval
Viewer • Updated • 500 • 16 -
xiaoyuanliu/HELMET_icl_banking77_5900shot_balance__eval
Viewer • Updated • 500 • 12 -
xiaoyuanliu/HELMET_icl_trec_fine_6400shot_balance__eval
Viewer • Updated • 500 • 13 -
xiaoyuanliu/HELMET_icl_trec_coarse_6600shot_balance__eval
Viewer • Updated • 500 • 17
models 90
xiaoyuanliu/StateLM-14B-RL-0124-CKPT32
Text Generation • 15B • Updated • 9
xiaoyuanliu/StateLM-8B-RL-0123-CKPT32
Text Generation • 8B • Updated • 11
xiaoyuanliu/StateLM-4B-SFT
Text Generation • 4B • Updated • 8
xiaoyuanliu/StateLM-14B-SFT
Text Generation • 15B • Updated • 8
xiaoyuanliu/StateLM-8B-SFT
Text Generation • 8B • Updated • 9
xiaoyuanliu/Qwen3-30B-A3B-SFT-V4_OPT
Text Generation • 31B • Updated • 4
xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo-verifier
Text Generation • 2B • Updated • 11
xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-verifier
Text Generation • 3B • Updated • 15
xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-verifier
Text Generation • 8B • Updated • 10
xiaoyuanliu/Qwen3-4B-SFT-V2.1-ml.16K-lr.1e-5-ep.3
Text Generation • 4B • Updated • 12
datasets 72
xiaoyuanliu/statelm_v4opt
Viewer • Updated • 35.7k • 38
xiaoyuanliu/mmlu-redux
Viewer • Updated • 3k • 20
xiaoyuanliu/LongBench-v2-verified
Viewer • Updated • 503 • 22
xiaoyuanliu/claude4-agentic-samples-V4-opt-swift-format-500
Viewer • Updated • 500 • 15
xiaoyuanliu/claude4-agentic-samples-V4-opt-swift-format
Viewer • Updated • 35.7k • 25
xiaoyuanliu/V4-BAScan-Warmup360
Viewer • Updated • 7.17k • 15
xiaoyuanliu/longmemeval-s
Viewer • Updated • 500 • 28
xiaoyuanliu/LongBench-v2-rlvr
Viewer • Updated • 503 • 26
xiaoyuanliu/LongBench-v2-T100
Viewer • Updated • 100 • 19
xiaoyuanliu/V4-BA-Warmup300
Viewer • Updated • 3.72k • 13