Article
12
Zidi Xiong
polaris-73
AI & ML interests
None yet
Recent Activity
updated a collection 11 days ago
Monitorability as a Free Gift published a dataset 11 days ago
polaris-73/monitorability-as-a-free-gift-data-training-data updated a dataset 11 days ago
polaris-73/monitorability-as-a-free-gift-data-training-dataOrganizations
Checkpoints for Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning
-
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Text Generation • 2B • Updated • 648k • • 1.56k -
Qwen/Qwen3-4B
Text Generation • 4B • Updated • 4.79M • • 682 -
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Text Generation • 8B • Updated • 411k • • 874 -
polaris-73/DeepSeek-R1-Distill-Qwen-1.5B-RLVR-Science-step-100
2B • Updated • 4
Checkpoints for Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning
-
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Text Generation • 2B • Updated • 648k • • 1.56k -
Qwen/Qwen3-4B
Text Generation • 4B • Updated • 4.79M • • 682 -
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Text Generation • 8B • Updated • 411k • • 874 -
polaris-73/DeepSeek-R1-Distill-Qwen-1.5B-RLVR-Science-step-100
2B • Updated • 4
models 242
polaris-73/DeepSeek-R1-Distill-Qwen-1.5B-RLVR-Math-step-800
2B • Updated • 10
polaris-73/DeepSeek-R1-Distill-Qwen-1.5B-RLVR-Math-step-700
2B • Updated • 3
polaris-73/DeepSeek-R1-Distill-Qwen-1.5B-RLVR-Math-step-600
2B • Updated • 5
polaris-73/DeepSeek-R1-Distill-Qwen-1.5B-RLVR-Math-step-500
2B • Updated • 7
polaris-73/DeepSeek-R1-Distill-Llama-8B-RLVR-Math-step-400
8B • Updated • 5
polaris-73/ds1p5b_skywork_math_cliphigh-global_step_500
2B • Updated • 4
polaris-73/ds1p5b_skywork_math_cliphigh-global_step_400
2B • Updated • 5
polaris-73/ds1p5b_skywork_math_cliphigh-global_step_300
2B • Updated • 4
polaris-73/DeepSeek-R1-Distill-Llama-8B-RLVR-IF-step-800
8B • Updated • 7
polaris-73/DeepSeek-R1-Distill-Llama-8B-RLVR-IF-step-700
8B • Updated • 8