You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

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.		3 months ago
..
UnslothGRPOTrainerTemp.py	chore: disable logging, enable torch complie	3 months ago
__init__.py	feat: enhance evaluation script and remove deprecated shell script	3 months ago
agent.py	feat: enhance evaluation script and remove deprecated shell script	3 months ago
config.py	feat: refactor whole code base, add logic for training R1 distil base models, change some template and reward logics	3 months ago
embeddings.py	refactor: restructure code base, better centralize logging logic	3 months ago
evaluation.py	feat: update training and evaluation configurations (editable agent generation scripts)	3 months ago
prompts.py	feat: refine user prompt logic for improved clarity and structure	3 months ago
rewards.py	feat: enhance reward_retry function to handle missing answer tags	3 months ago
search_module.py	feat: refactor whole code base, add logic for training R1 distil base models, change some template and reward logics	3 months ago
tokenizer_adapter.py	feat: add code for qwen architecture	3 months ago