quancute/DPOLlama-3.2-1B-Instruct_sum-chosen5_reject_less2-5k_22Mar-2025_A100 1B • Updated Mar 23 • 3
quancute/DPOLlama-3.2-1B-Instruct_sum-chosen5_reject_greater3-20k_22Mar-2025_A100 1B • Updated Mar 23 • 3
quancute/DPOVit5-10k_plus4domain_from_24k-21Mar-2025-A100-new Text Generation • 0.8B • Updated Mar 22 • 2
quancute/Best-DPOVit5-10k_plus4domain_from_24k-21Mar-2025-A100-new Text Generation • 0.8B • Updated Mar 22 • 5