A framework for training LLM agents via RL with advanced search capability: https://github.com/Tree-Shu-Zhao/ferret
Shu Zhao PRO
TreezzZ
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
The Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors authored a paper 1 day ago
MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition updated a dataset 2 days ago
TreezzZ/SMILE-dataOrganizations
models 14
TreezzZ/Ferret_Search-R1_Qwen2.5-14b-instruct_ppo
15B • Updated • 4
TreezzZ/Ferret_ParallelSearch_Qwen3-30b-a3b-instruct_ppo
31B • Updated • 6
TreezzZ/Ferret_ParallelSearch_Qwen2.5-3b-instruct_ppo
3B • Updated • 5
TreezzZ/Ferret_ParallelSearch_Qwen3-4b-instruct_ppo
4B • Updated • 5
TreezzZ/Ferret_ExpandSearch_Qwen2.5-3b-instruct_Llama4-Maverick-17b-128e-instruct_ppo
3B • Updated • 8
TreezzZ/Ferret_ParallelSearch_Qwen2.5-7b-instruct_ppo
8B • Updated • 13
TreezzZ/Ferret_Search-R1_Qwen2.5-3b-instruct_ppo
3B • Updated • 7
TreezzZ/ExpandSearch-3b-instruct-Squeezer-LLaMA4-Maverick
3B • Updated • 8
TreezzZ/ParallelSearch-7b-base
8B • Updated • 12 • 1
TreezzZ/ParallelSearch-7b-instruct
8B • Updated • 12 • 2
datasets 7
TreezzZ/SMILE-data
Updated • 84
TreezzZ/MoRA-data
Preview • Updated • 473
TreezzZ/ParallelSearch
Viewer • Updated • 59.5k • 33
TreezzZ/parsearch
Preview • Updated • 10
TreezzZ/multihoprag-index
Viewer • Updated • 40.5k • 25
TreezzZ/bumblebee
Viewer • Updated • 26.8k • 14
TreezzZ/WebQA
Viewer • Updated • 41.7k • 129 • 1