THU-KEG/OpenSAE-LLaMA-3.1-Layer_05
2B
•
Updated
•
1
AI & ML interests
None defined yet.
Recent Activity
Papers
DeepPrune: Parallel Scaling without Inter-trace Redundancy
SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression
THU-KEG/OpenSAE-LLaMA-3.1-Layer_04
2B
•
Updated
•
8
THU-KEG/OpenSAE-LLaMA-3.1-Layer_03
2B
•
Updated
•
8
THU-KEG/OpenSAE-LLaMA-3.1-Layer_02
2B
•
Updated
THU-KEG/OpenSAE-LLaMA-3.1-Layer_01
2B
•
Updated
•
8
THU-KEG/OpenSAE-LLaMA-3.1-Layer_00
2B
•
Updated
•
22
THU-KEG/ADELIE-DPO-1.5B
Text Generation
•
Updated
•
64
•
5
THU-KEG/ADELIE-DPO-3B
Text Generation
•
Updated
•
30
•
2
THU-KEG/ADELIE-SFT-1.5B
Text Generation
•
Updated
•
35
THU-KEG/ADELIE-SFT-3B
Text Generation
•
Updated
•
28
•
2
THU-KEG/ADELIE-DPO
Text Generation
•
Updated
•
42
•
3
THU-KEG/ADELIE-SFT
Text Generation
•
Updated
•
34
•
6
THU-KEG/Llama3-Crab-DPO
Text Generation
•
Updated
•
2
THU-KEG/Llama3-Crab-SFT
Text Generation
•
Updated
THU-KEG/Mistral-Crab-DPO
Text Generation
•
7B
•
Updated
•
2
•
4
THU-KEG/Mistral-Crab-SFT
Text Generation
•
7B
•
Updated
•
5
THU-KEG/kopl_semantic_parser
Text Generation
•
Updated
•
3
•
1
THU-KEG/LLMAEL-ReFinED-FT
Updated
•
5
•
3