Several trained models to compare the differences between each method. Each model has a complete description of hyperparams with wandb reports.
G
G-reen
AI & ML interests
SFT, DPO, ORPO, LLMs, text-generation
Recent Activity
updated
a dataset
about 2 hours ago
G-reen/mixed_prompts_thinking_left_fixed
published
a dataset
about 2 hours ago
G-reen/mixed_prompts_thinking_left_fixed
updated
a dataset
about 2 hours ago
G-reen/mixed_prompts_thinking_right_fixed
Organizations
None yet