PhoenixHu/grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint26312_bleu1_bleu4_0407 1.0B • Updated Apr 8 • 2
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint26312_bleu1_rouge4_kl3_temp07_0407 Updated Apr 8
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint26312_bleu1_rouge4_kl3_0407_metta Updated Apr 8
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint26312_bleu1_rouge4_kl05_temp07_0407 Updated Apr 8
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint26312_bleu1_rouge4_kl05_0407_metta Updated Apr 8
PhoenixHu/finetune_stage1_broad_h2s_1_open_1_yt_1_global64_lora64_newalldata_0406_metta Updated Apr 8
PhoenixHu/finetune_stage1_broad_h2s_1_open_1_yt_1_global64_lora32_newalldata_0406_metta Updated Apr 8
PhoenixHu/finetune_stage1_broad_h2s_1_open_1_yt_1_global64_lora16_newalldata_0406_metta Updated Apr 8
PhoenixHu/grpo_ral_internvl2_5_finetune_stage1_broad_h2s_1_open_1_youtube_1_0319_attention5_temperature07 Updated Apr 7
PhoenixHu/grpo_ral_internvl2_5_finetune_stage1_broad_h2s_1_open_1_youtube_1_0319_attention3_temperature07 Updated Apr 6
PhoenixHu/grpo_internvl2_5_finetune_stage1_broad_h2s_1_open_1_youtube_1_0319_temperature07 0.9B • Updated Apr 6 • 2