THU-KEG/OpenSAE-LLaMA-3.1-Layer_00-shift_back
2B
•
Updated
•
7
AI & ML interests
None defined yet.
Papers
DeepPrune: Parallel Scaling without Inter-trace Redundancy
SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression
THU-KEG/OpenSAE-LLaMA-3.1-Layer_31
2B
•
Updated
•
7
THU-KEG/OpenSAE-LLaMA-3.1-Layer_30
2B
•
Updated
•
6
THU-KEG/OpenSAE-LLaMA-3.1-Layer_29
2B
•
Updated
•
7
THU-KEG/OpenSAE-LLaMA-3.1-Layer_28
2B
•
Updated
•
6
THU-KEG/OpenSAE-LLaMA-3.1-Layer_27
2B
•
Updated
•
6
THU-KEG/OpenSAE-LLaMA-3.1-Layer_26
2B
•
Updated
•
7
THU-KEG/OpenSAE-LLaMA-3.1-Layer_25
2B
•
Updated
•
7
THU-KEG/OpenSAE-LLaMA-3.1-Layer_24
2B
•
Updated
•
6
THU-KEG/OpenSAE-LLaMA-3.1-Layer_23
2B
•
Updated
•
4
THU-KEG/OpenSAE-LLaMA-3.1-Layer_22
2B
•
Updated
•
8
THU-KEG/OpenSAE-LLaMA-3.1-Layer_21
2B
•
Updated
•
6
THU-KEG/OpenSAE-LLaMA-3.1-Layer_20
2B
•
Updated
•
9
THU-KEG/OpenSAE-LLaMA-3.1-Layer_19
2B
•
Updated
•
5
THU-KEG/OpenSAE-LLaMA-3.1-Layer_18
2B
•
Updated
•
7
THU-KEG/OpenSAE-LLaMA-3.1-Layer_17
2B
•
Updated
•
6
THU-KEG/OpenSAE-LLaMA-3.1-Layer_16
2B
•
Updated
•
9
THU-KEG/OpenSAE-LLaMA-3.1-Layer_15
2B
•
Updated
•
6
THU-KEG/OpenSAE-LLaMA-3.1-Layer_14
2B
•
Updated
•
13
THU-KEG/OpenSAE-LLaMA-3.1-Layer_13
2B
•
Updated
•
6
THU-KEG/OpenSAE-LLaMA-3.1-Layer_12
2B
•
Updated
•
9
THU-KEG/OpenSAE-LLaMA-3.1-Layer_11
2B
•
Updated
•
4
THU-KEG/OpenSAE-LLaMA-3.1-Layer_10
2B
•
Updated
•
5
THU-KEG/OpenSAE-LLaMA-3.1-Layer_09
2B
•
Updated
•
5
THU-KEG/OpenSAE-LLaMA-3.1-Layer_08
2B
•
Updated
•
5
THU-KEG/OpenSAE-LLaMA-3.1-Layer_07
2B
•
Updated
•
4
THU-KEG/OpenSAE-LLaMA-3.1-Layer_06
2B
•
Updated
•
5
THU-KEG/OpenSAE-LLaMA-3.1-Layer_05
2B
•
Updated
•
5
THU-KEG/OpenSAE-LLaMA-3.1-Layer_04
2B
•
Updated
•
5
THU-KEG/OpenSAE-LLaMA-3.1-Layer_03
2B
•
Updated
•
4