AnnaelleMyriam/MNLP_M3_sft_dpo_1024_beta0.5_2e-5_FINAL_v4_16b_57k_check1500 Text Generation • 0.6B • Updated Jun 10 • 8
AnnaelleMyriam/MNLP_M3_dpo_1024_beta0.5_2e-5_FINAL_v5_16_check1500 Text Generation • 0.6B • Updated Jun 10 • 6
AnnaelleMyriam/MNLP_M3_sft_dpo_1024_beta0.5_2e-5_FINAL_v3_16_check1200 Text Generation • 0.6B • Updated Jun 10 • 7
AnnaelleMyriam/MNLP_M3_sft_dpo_1024_beta0.5_2e-5_FINAL_v3_16_check1500 Text Generation • 0.6B • Updated Jun 10 • 11
AnnaelleMyriam/MNLP_M3_sft_dpo_1024_beta0.5_2e-5_FINAL_v4_16b_57k_check2100 Text Generation • 0.6B • Updated Jun 10 • 6
AnnaelleMyriam/MNLP_M3_sft_dpo_1024_beta0.5_2e-5_FINAL_v4_16b_check1800 Text Generation • 0.6B • Updated Jun 10 • 7
AnnaelleMyriam/MNLP_M3_sft_dpo_1024_beta0.5_2e-5_FINAL_v4_16b_57k_check1800 Text Generation • 0.6B • Updated Jun 10 • 6
AnnaelleMyriam/MNLP_M3_sft_dpo_1024_beta0.5_2e-5_FINAL_v3_16_check1050 Text Generation • 0.6B • Updated Jun 9 • 7
AnnaelleMyriam/MNLP_M3_sft_dpo_1024_beta0.1_2e-5_FINAL_chk34000 Text Generation • 0.6B • Updated Jun 9 • 8
AnnaelleMyriam/MNLP_M3_sft_dpo_1024_beta0.1_2e-5_FINAL_chk38000 Text Generation • 0.6B • Updated Jun 9 • 8
AnnaelleMyriam/MNLP_M3_sft_dpo_1024_beta0.1_2e-5_FINAL_chk30000 Text Generation • 0.6B • Updated Jun 9 • 7
AnnaelleMyriam/MNLP_M3_sft_dpo_1024_beta0.5_2e-5_check40000 Text Generation • 0.6B • Updated Jun 9 • 7
AnnaelleMyriam/MNLP_M3_sft_dpo_1024_beta0.5_2e-5_check34000 Text Generation • 0.6B • Updated Jun 9 • 5
AnnaelleMyriam/MNLP_M2_sft_dpo_1024_beta0.1_2e-5_chk48000 Text Generation • 0.6B • Updated Jun 7 • 10