Nguyen Hoang Phi
nghgphi
AI & ML interests
None yet
Organizations
None yet
models 10
nghgphi/tofu_Llama-3.2-1B-Instruct_forget01_PDU
Updated
nghgphi/tofu_Llama-3.2-1B-Instruct_forget01_NPO
1B • Updated • 5
nghgphi/tofu_Llama-3.2-1B-Instruct_forget01_GradDiff
1B • Updated • 4
nghgphi/tofu_Llama-3.2-1B-Instruct_forget01_GradAscent
1B • Updated • 4
nghgphi/tofu_Llama-3.2-1B-Instruct_forget01_DPO
1B • Updated • 5
nghgphi/tofu_Llama-3.2-1B-Instruct_forget01_CEU
1B • Updated • 4
nghgphi/lr5e-5_g1e-4_ompaper_etop0.6_kltrue_k0.01_kmin-5.0_kmax5.0_test-entropy-top-ratio
Updated
nghgphi/lr5e-5_g1e-4_ompaper_etop0.4_kltrue_k0.01_kmin-5.0_kmax5.0_test-entropy-top-ratio
Updated
nghgphi/dpo-rollout-mistralai-ultrafeedback
Updated
nghgphi/qwen_alpha_iter0-ckpt_merged
2B • Updated • 6