PhoenixHu/grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint39570_bleu1_rouge_temp07_0408 1.0B • Updated Apr 10 • 4
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint39570_bleu1_rouge_kl3_temp07_0408 Updated Apr 10
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint39570_bleu1_rouge4_kl3_temp07_0408 Updated Apr 10
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint32890_bleu1_rouge_kl05_temp07_0407 Updated Apr 10
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint32890_bleu1_rouge4_kl05_temp07_0407 Updated Apr 10
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint31656_bleu1_rouge_kl3_temp07_0408 Updated Apr 10
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora16_checkpoint39570_bleu1_rouge_kl3_temp07_0408 Updated Apr 10
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora16_checkpoint39570_bleu1_rouge4_kl3_temp07_0408 Updated Apr 10
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint31656_bleu1_rouge4_kl3_temp07_0408 Updated Apr 10
PhoenixHu/grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint39570_bleu1_bleu4_temp07_0408 1.0B • Updated Apr 10 • 2
PhoenixHu/grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint32890_bleu1_rouge_temp07_0407 1.0B • Updated Apr 10 • 6
PhoenixHu/grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint31656_bleu1_rouge_temp07_0408 1.0B • Updated Apr 10 • 4
PhoenixHu/grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint31656_bleu1_bleu4_temp07_0408 1.0B • Updated Apr 10 • 4
PhoenixHu/grpo_internvl2_5_how2sign_1b_global64_lora16_checkpoint39570_bleu1_rouge_temp07_0408 1.0B • Updated Apr 10 • 4
PhoenixHu/grpo_internvl2_5_how2sign_1b_global64_lora16_checkpoint39570_bleu1_bleu4_temp07_0408 1.0B • Updated Apr 10 • 4
PhoenixHu/grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint32890_bleu1_bleu4_temp07_0407 1.0B • Updated Apr 8 • 3
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint32890_bleu1_rouge4_kl3_temp07_0407 Updated Apr 8
PhoenixHu/ral_grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint32890_bleu1_rouge_kl3_temp07_0407 Updated Apr 8
PhoenixHu/finetune_stage1_broad_h2s_1_open_1_yt_1_global64_lora32_newdata_0403_metta 1.0B • Updated Apr 8 • 3 • 1
PhoenixHu/grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint26312_bleu1_bleu4_temp07_0407 1.0B • Updated Apr 8 • 2
PhoenixHu/grpo_internvl2_5_how2sign_1b_global64_lora64_checkpoint26312_bleu1_bleu4_0407 1.0B • Updated Apr 8 • 3
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