Phi PRO
Xalphinions
AI & ML interests
None yet
Recent Activity
upvoted a collection 33 minutes ago
MARS authored a paper 2 days ago
Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models authored a paper 2 days ago
Document Reconstruction Unlocks Scalable Long-Context RLVROrganizations
models 16
Xalphinions/MARS-Qwen2.5-0.5B-blk8
0.6B • Updated • 23
Xalphinions/MARS-Qwen2.5-0.5B-AR-SFT
0.6B • Updated • 24
Xalphinions/MARS-Qwen2.5-0.5B-blk16
0.6B • Updated • 22
Xalphinions/MARS-Qwen2.5-0.5B-blk8-no-sft
0.6B • Updated • 23
Xalphinions/MARS-Qwen2.5-0.5B-blk4-no-sft
0.6B • Updated • 24
Xalphinions/MARS-Qwen2.5-0.5B-blk4
0.6B • Updated • 22
Xalphinions/MARS-Qwen2.5-0.5B-blk16-no-sft
0.6B • Updated • 24
Xalphinions/MARS-Qwen2.5-7B-blk4
8B • Updated • 26
Xalphinions/MARS-Qwen2.5-7B-AR-SFT
8B • Updated • 30
Xalphinions/MARS-Qwen2.5-0.5B-BD3LM-blk4
0.6B • Updated • 26
datasets 10
Xalphinions/olmo-verified-data
Viewer • Updated • 21.1k • 17
Xalphinions/transformed_long_story_short_no_strip
Viewer • Updated • 17.6k • 4 • 1
Xalphinions/UltraFeedback_with_tie_armorm_1e-2_non_zero_2
Viewer • Updated • 22k • 4
Xalphinions/UltraFeedback_with_tie_armorm_1e-2_non_zero
Viewer • Updated • 22k • 4
Xalphinions/UltraFeedback_with_tie_armorm_1e-4
Viewer • Updated • 20.3k • 5
Xalphinions/UltraFeedback_with_tie_armorm
Viewer • Updated • 26.6k • 5
Xalphinions/UltraFeedback_with_tie_strict
Viewer • Updated • 65.1k • 7
Xalphinions/llama3_ultrafeedback_with_tie_armorm
Viewer • Updated • 61.8k • 6
Xalphinions/UltraFeedback_with_tie
Viewer • Updated • 133k • 6
Xalphinions/llama3_ultrafeedback_with_tie
Viewer • Updated • 61.8k • 4