Pretrained Checkpoints of LLMs
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training
RePro: Training Language Models to Faithfully Recycle the Web for Pretraining
models 6
cx-cmu/ReScraper
Text Generation • Updated
cx-cmu/AutoGEO_mini_Qwen1.7B_ResearchyGEO
Text Generation • 2B • Updated • 54
cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench
Text Generation • 2B • Updated • 82
cx-cmu/AutoGEO_mini_Qwen1.7B_Ecommerce
Text Generation • 2B • Updated • 49
cx-cmu/repro-rephraser-4B
Text Generation • 196k • Updated • 52 • 2
cx-cmu/repro-rephraser-1B
Text Generation • 1B • Updated • 93
datasets 14
cx-cmu/IdeaTaste
Viewer • Updated • 275k • 218
cx-cmu/ReScraper-Data
Viewer • Updated • 22.2M • 230
cx-cmu/EmbodiedMidtrain-RealWorld-Eval
Updated • 33
cx-cmu/AgentWebBench-corpus
Viewer • Updated • 1 • 567
cx-cmu/agent_trajectories
Updated • 183 • 4
cx-cmu/deepresearchgym-agentic-search-logs
Viewer • Updated • 14.3M • 232 • 16
cx-cmu/Researchy-GEO
Viewer • Updated • 47k • 122 • 2
cx-cmu/GEO-Bench
Viewer • Updated • 37.4k • 182 • 2
cx-cmu/E-commerce
Viewer • Updated • 7.97k • 162 • 2
cx-cmu/ClueWeb-Reco
Viewer • Updated • 87.2M • 58 • 1