arxiv:2408.06292
Chris Lu
chrlu
AI & ML interests
None yet
Organizations
models
19
chrlu/zephyr-7b-gemma-bline-kto-unlabeled
Text Generation
•
Updated
•
16
chrlu/zephyr-7b-gemma-kto-2
Text Generation
•
Updated
•
18
chrlu/zephyr-7b-gemma-adaptive_confidence_margin_loss_213
Text Generation
•
Updated
•
18
chrlu/zephyr-7b-gemma-adaptive_quantile_feedback_loss
Text Generation
•
Updated
•
16
chrlu/zephyr-7b-gemma-dynamic_blended_adaptive_quantile_loss
Text Generation
•
Updated
•
19
chrlu/zephyr-7b-gemma-adaptive_blended_loss_with_temperature_scaling
Text Generation
•
Updated
•
18
chrlu/zephyr-7b-gemma-log_ratio_modulated_loss
Text Generation
•
Updated
•
16
chrlu/zephyr-7b-gemma-policy_focused_loss
Text Generation
•
Updated
•
18
chrlu/zephyr-7b-gemma-combined_exp_logistic_loss
Text Generation
•
Updated
•
17
chrlu/zephyr-7b-gemma-adaptive_quantile_loss
Text Generation
•
Updated
•
17
datasets
None public yet