resistz/TTCL-Law-RLCR-Qwen3-8B-DAPO-Math14K
8B • Updated • 18
Zizhuo Zhang PRO
resistz
AI & ML interests
None yet
Recent Activity
updated a collection 19 days ago
Test-time Calibration Learning (TTCL) Models updated a collection 19 days ago
Test-time Calibration Learning (TTCL) Models updated a collection 19 days ago
Test-time Calibration Learning (TTCL) ModelsOrganizations
resistz/TTCL-ChineseSimpleQA-RLCR-InternLM3-8B-Instruct-DAPO-Math14K
9B • Updated • 42
resistz/TTCL-Law-Llama-3.1-8B-Instruct
8B • Updated • 24
resistz/TTCL-TriviaQA-RLCR-Llama-3.1-8B-Instruct-DAPO-Math14K
8B • Updated • 17
resistz/TTCL-HotpotQA-RLCR-Llama-3.1-8B-Instruct-DAPO-Math14K
8B • Updated • 21
resistz/TTCL-NQ-RLCR-Llama-3.1-8B-Instruct-DAPO-Math14K
8B • Updated • 25
resistz/TTCL-Finance-RLCR-Qwen3-8B-DAPO-Math14K
8B • Updated • 16
resistz/TTCL-Finance-RLCR-Llama-3.1-8B-Instruct-DAPO-Math14K
8B • Updated • 33
resistz/RLCR-Calibrated-Llama-3.1-8B-Instruct-DAPO-Math14K-40Step
8B • Updated • 9
resistz/TTCL-SimpleQA-RLCR-Internlm3-8B-Instruct-DAPO-Math14K
9B • Updated • 15
resistz/RLCR-Calibrated-Internlm3-8B-Instruct-DAPO-Math14K
9B • Updated • 18
resistz/TTCL-SimpleQA-RLCR-Llama-3.1-8B-Instruct-DAPO-Math14K
8B • Updated • 9
resistz/TTCL-ChineseSimpleQA-RLCR-Llama-3.1-8B-Instruct-DAPO-Math14K
8B • Updated • 13
resistz/SFT_Llama-3.1-8B-Instruct_Math2K_FactQA2K_Correct
8B • Updated • 7
resistz/Answer100-Abstain0-SymmetricReward-Qwen3-4B
4B • Updated • 4
resistz/Answer75-Abstain25-SymmetricReward-Qwen3-4B
4B • Updated • 4
resistz/Answer50-Abstain50-SymmetricReward-Qwen3-4B
4B • Updated • 4
resistz/Answer25-Abstain75-SymmetricReward-Qwen3-4B
4B • Updated • 5
resistz/Answer0-Abstain100-SymmetricReward-Qwen3-4B
4B • Updated • 4
resistz/Answer100-Abstain0-SymmetricReward-Llama-3.2-3B-Instruct
4B • Updated • 10
resistz/Answer75-Abstain25-SymmetricReward-Llama-3.2-3B-Instruct
4B • Updated • 9
resistz/Answer50-Abstain50-SymmetricReward-Llama-3.2-3B-Instruct
4B • Updated • 10
resistz/Answer25-Abstain75-SymmetricReward-Llama-3.2-3B-Instruct
4B • Updated • 7
resistz/Answer0-Abstain100-SymmetricReward-Llama-3.2-3B-Instruct
4B • Updated • 9
resistz/Answer100-Abstain0-SymmetricReward-Llama-3.1-8B-Instruct
8B • Updated • 5
resistz/Answer75-Abstain25-SymmetricReward-Llama-3.1-8B-Instruct
8B • Updated • 4
resistz/Answer50-Abstain50-SymmetricReward-Llama-3.1-8B-Instruct
8B • Updated • 6
resistz/Answer25-Abstain75-SymmetricReward-Llama-3.1-8B-Instruct
8B • Updated • 6
resistz/Answer0-Abstain100-SymmetricReward-Llama-3.1-8B-Instruct
8B • Updated • 5
resistz/PairContext-Qwen3-1.7B
0.8B • Updated • 5