24 Commits (9738b80353c9be77e4b0ac2163274d29354dfd2a)

Author	SHA1	Message	Date
thinhlpg	bec864038b	feat: increase max tokens and new tokens in evaluation scripts	4 weeks ago
thinhlpg	424459d840	feat: update evaluation scripts to enhance model configuration and dataset loading, including increased max tokens and added logging	4 weeks ago
thinhlpg	504f0c6c8e	feat: update reward_em_chunk to match only the LAST required paragraph of the reasoning chain and adjust related tests	4 weeks ago
thinhlpg	358875a035	feat: enhance reward_em_chunk function to match multiple paragraphs, add test	4 weeks ago
thinhlpg	2df9f39fda	feat: update model configuration (longer context) and dataset loading logic for improved performance and flexibility	4 weeks ago
thinhlpg	4a1d45271d	feat: add scripts for musique data processing	4 weeks ago
thinhlpg	eebf914a81	refactor: moved modules from src/deepsearch to src/	1 month ago
thinhlpg	0f662d4330	refactor: moved FlashRAG submodule from src/ to third_party/	1 month ago
thinhlpg	55f34b8503	feat: add FlashRAG as submodule	1 month ago
thinhlpg	2fec4f2f42	refactor: change repo stucture (move code from src/ to src/deepsearch)	1 month ago
thinhlpg	010957cd99	feat: disable randomization option to get_qa_dataset function by default	1 month ago
thinhlpg	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.	1 month ago
thinhlpg	c8714e0f6b	feat: enhance reward_retry function to handle missing answer tags ... Added logic to return 0 if the final message from the assistant does not contain answer tags (no matter how hard you try, you won't get anything if no result 💀)	1 month ago
thinhlpg	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.	1 month ago
thinhlpg	d0e6068055	fix: strengthen reward correctness logic to handle final message is not asnwer form assistant. Also update logs for reward functions for better debug ... - Added 'logs/' directory to .gitignore to exclude log files. - Introduced log_chat_state function to log chat states and rewards to JSONL files. - Updated reward functions to log chat states with validation results for better tracking and debugging.	1 month ago
thinhlpg	338655e563	feat: refine user prompt logic for improved clarity and structure	1 month ago
thinhlpg	6d994feeb2	feat: enhance evaluation scripts for base and LoRA models	1 month ago
thinhlpg	af7f38c792	feat: add code for qwen architecture	1 month ago
thinhlpg	9009440663	chore: disable logging, enable torch complie	1 month ago
thinhlpg	d2f03b96ab	feat: enhance evaluation script and remove deprecated shell script ... - Updated eval.py to streamline model evaluation using vLLM and unsloth. - Deleted eval.sh as its functionality is now integrated into eval.py. - Updated .gitignore to exclude eval_logs directory.	1 month ago
thinhlpg	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	1 month ago
thinhlpg	c90c03267e	feat: change user prompt template to search-r1 inspried format ... use <search></search> instead of embed whole tool definition, which resulted in lots or parsing errors	1 month ago
thinhlpg	04593fa8fd	style: change line length to 119, organize imports	1 month ago
thinhlpg	3c2deaced9	refactor: restructure code base, better centralize logging logic	1 month ago