A framework for training LLM agents via RL with advanced search capability: https://github.com/Tree-Shu-Zhao/ferret
Shu Zhao
TreezzZ
AI & ML interests
None yet
Recent Activity
updated a dataset about 1 month ago
TreezzZ/MoRA-data authored a paper about 1 month ago
ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning updated a collection 9 months ago
FerretOrganizations
models 14
TreezzZ/Ferret_Search-R1_Qwen2.5-14b-instruct_ppo
15B • Updated • 1
TreezzZ/Ferret_ParallelSearch_Qwen3-30b-a3b-instruct_ppo
31B • Updated • 2
TreezzZ/Ferret_ParallelSearch_Qwen2.5-3b-instruct_ppo
3B • Updated • 1
TreezzZ/Ferret_ParallelSearch_Qwen3-4b-instruct_ppo
4B • Updated • 1
TreezzZ/Ferret_ExpandSearch_Qwen2.5-3b-instruct_Llama4-Maverick-17b-128e-instruct_ppo
3B • Updated • 1
TreezzZ/Ferret_ParallelSearch_Qwen2.5-7b-instruct_ppo
8B • Updated • 1
TreezzZ/Ferret_Search-R1_Qwen2.5-3b-instruct_ppo
3B • Updated • 1
TreezzZ/ExpandSearch-3b-instruct-Squeezer-LLaMA4-Maverick
3B • Updated • 1
TreezzZ/ParallelSearch-7b-base
8B • Updated • 157 • 1
TreezzZ/ParallelSearch-7b-instruct
8B • Updated • 2 • 2