Shirley Wu

shirwu 's models 44

Sort:  Recently updated

shirwu/rm_debug_unfreeze-last_quant_Skywork-Reward-Llama-3.1-8B-v0.2

Updated Feb 14, 2025

shirwu/rm_freeze_last_Skywork-Reward-Llama-3.1-8B-v0.2

Updated Feb 14, 2025

shirwu/rm_unfreeze_old_template_last_Llama-3.1-8B-Instruct

Updated Feb 14, 2025

shirwu/rm_freeze_1e-4_last_Skywork-Reward-Llama-3.1-8B-v0.2

Updated Feb 14, 2025

shirwu/rm_unfreeze_last_Skywork-Reward-Llama-3.1-8B-v0.2

Updated Feb 13, 2025

shirwu/rm_train_Skywork-Reward-Llama-3.1-8B-v0.2

Updated Feb 13, 2025

shirwu/rm_train_Llama-3.1-8B-Instruct

Updated Feb 13, 2025

shirwu/mulitgpu

Updated Feb 12, 2025

shirwu/preference_iterative_hard-answer_generator-iter0

Text Classification • 8B • Updated Feb 12, 2025 • 2

shirwu/content

Updated Oct 19, 2024 • 2

shirwu/dpo-personal-preference-llama3.2-1b-tokenizer

Updated Oct 19, 2024

shirwu/dpo-personal-preference-llama3.2-1b-model

Updated Oct 19, 2024

shirwu/Meta-Llama-3-8B-Instruct_epoch-300_lr-2e-05

Updated Sep 1, 2024

shirwu/Meta-Llama-3-8B-Instruct_epoch-3_lr-2e-05

Updated Sep 1, 2024