eebf914a81
refactor: moved modules from src/deepsearch to src/
3 months ago
2fec4f2f42
refactor: change repo stucture (move code from src/ to src/deepsearch)
3 months ago
1a18cd7bfd
feat: update training and evaluation configurations (editable agent generation scripts)
...
Increased max_generations parameter in agentic_generate and run_eval functions for improved output flexibility.
3 months ago
bf480574a2
fix: minor bug
3 months ago
4de31e0f30
feat: expand reward functions with new strategies and diversity checks
...
- Added reward functions for search strategy and search diversity
- Updated reward_format to include validation for proper message endings.
3 months ago
af7f38c792
feat: add code for qwen architecture
3 months ago
31dcbf5d8a
feat: refactor whole code base, add logic for training R1 distil base models, change some template and reward logics
...
- Break down rl_helpers into smaller modules
- Removed deprecated rl_helpers module to streamline the codebase.
- Enhance initial user prompt template inspired by Search-R1
3 months ago
da79e986b6
feat: add new script and functionality in train script to save model in 16 bit format
3 months ago
04593fa8fd
style: change line length to 119, organize imports
3 months ago
3c2deaced9
refactor: restructure code base, better centralize logging logic
3 months ago
thinhlpg