Yufeng Xu
Zephyr271828
AI & ML interests
MLSys; NLP; RL
Recent Activity
upvoted a paper about 2 months ago
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering updated a dataset 3 months ago
Zephyr271828/quest-qwen3-122b-a10b-raw published a dataset 3 months ago
Zephyr271828/quest-qwen3-122b-a10b-rawOrganizations
models 25
Zephyr271828/Qwen3.5-4B-OpenSeeker-MiroVerse-Mix-SFT
5B • Updated • 2
Zephyr271828/Qwen3.5-4B-OpenSeeker-v1-SFT
5B • Updated • 4
Zephyr271828/qwen3-4b-openseeker-step456
4B • Updated • 2
Zephyr271828/qwen3-4b-openseeker-step304
4B • Updated • 2
Zephyr271828/flap_ablate_kv5_h4096_m6528_WIFV_UL-MM_llama3.1-8b-l200
4B • Updated • 7
Zephyr271828/flap_ablate_kv5_h4096_m6528_WIFV_UL-MM_Llama-3.1-8B
4B • Updated • 7
Zephyr271828/Sheared-Llama3-3456h-8kv-7808mlp
Updated • 4
Zephyr271828/Sheared-Llama3-3456h-7kv-7936mlp
Updated • 4
Zephyr271828/Sheared-Llama3-3456h-6kv-8064mlp
Updated • 4
Zephyr271828/Sheared-Llama3-3456h-5kv-8064mlp
Updated • 5
datasets 12
Zephyr271828/quest-qwen3-122b-a10b-raw
Viewer • Updated • 3.53k • 29
Zephyr271828/quest-qwen3-122b-a10b
Viewer • Updated • 2.58k • 11
Zephyr271828/openseeker-miroverse-mix-full
Viewer • Updated • 29k • 28
Zephyr271828/openseeker-miroverse-mix-1to1
Viewer • Updated • 9.9k • 20
Zephyr271828/openseeker_v1_sft
Viewer • Updated • 4.95k • 11
Zephyr271828/dclm-llama3-64-shuffled
Viewer • Updated • 3.87B • 18
Zephyr271828/dclm-llama3-tokenized-shuffled
Updated • 1.63k
Zephyr271828/redpajama-for-prune-llama3
Preview • Updated • 42
Zephyr271828/dapo-math-17k
Viewer • Updated • 17.4k • 7
Zephyr271828/dclm-260b
Updated • 986