PhoenixHu/grpo_stable_reasoning_nolow_075_1000steps_lora64_changetolora8_2e-50727
Updated
Phoenix Hu
PhoenixHu
AI & ML interests
None yet
Recent Activity
updated a model about 22 hours ago
PhoenixHu/grpo_stable_reasoning_nolow_075_1000steps_lora64_changetolora8_2e-50727 published a model about 22 hours ago
PhoenixHu/grpo_stable_reasoning_nolow_075_1000steps_lora64_changetolora8_2e-50727 updated a model 1 day ago
PhoenixHu/grpo_stable_reasoning_nolow_075_1000steps_lora64_changetolora8_5e-60726Organizations
None yet
PhoenixHu/grpo_stable_reasoning_nolow_075_1000steps_lora64_changetolora8_5e-60726
Updated
PhoenixHu/grpo_stable_reasoning_withlow_075_1000steps_lora64_changetolora8_5e-60726
Updated
PhoenixHu/grpo_stable_reasoning_withlow_075_1000steps_lora16_0725
Updated • 3
PhoenixHu/grpo_stable_reasoning_withlow_075_1000steps_lora64_0725
Updated • 3
PhoenixHu/grpo_stable_reasoning_withlow_075_1000steps_lora16_changetolora8_0725
Updated • 6
PhoenixHu/grpo_stable_reasoning_nolow_0722_075_1200steps_lora64_withlow_0723
Reinforcement Learning • Updated
PhoenixHu/grpo_stable_reasoning_nolow_0722_075_1200steps_lora64_0723
Reinforcement Learning • Updated
PhoenixHu/grpo_stable_reasoning_nolow_0722_075_1200steps
Reinforcement Learning • Updated
PhoenixHu/grpo_stable_reasoning_nolow_0722_075_1200steps_temp12
Reinforcement Learning • Updated
PhoenixHu/2026_07_21_08_19_25_cot_ratio_075_lora64_bucketv13
Updated
PhoenixHu/grpo_stable_reasoning_nolow_0719_075_0720
Reinforcement Learning • Updated
PhoenixHu/grpo_stable_reasoning_nolow_0719_8rollout_075_0720
Reinforcement Learning • Updated
PhoenixHu/grpo_stable_reasoning_2_1_nolow_0719_75_0720
Reinforcement Learning • Updated
PhoenixHu/grpo_stable_reasoning_nolow_02kl_0714
Reinforcement Learning • Updated
PhoenixHu/grpo_stable_reasoning_nolow_nokl_0714
Reinforcement Learning • Updated
PhoenixHu/grpo_stable_reasoning_nolow_0711
Reinforcement Learning • Updated
PhoenixHu/grpo_stable_reasoning_05_nnear10_nolow_0710
Reinforcement Learning • Updated
PhoenixHu/grpo_stable_reasoning_0709
Reinforcement Learning • Updated
PhoenixHu/2026_06_28_07_36_28_cot_ratio_060_egohist
Updated
PhoenixHu/2026_06_26_07_09_43_cot_ratio_075_egohist
Updated
PhoenixHu/2026_06_25_08_05_52_cot_ratio_075_internvl2_5
Updated
PhoenixHu/vla-ad-evaluation-results-summary
Updated
PhoenixHu/2026_06_23_21_14_18_cot_ratio_090
Updated
PhoenixHu/2026_06_23_00_20_22_cot_ratio_060
Updated
PhoenixHu/2026_06_22_06_54_43_cot_ratio_075_v12
Updated
PhoenixHu/internvl2_5-sft-meta-broad-h2s-0422
Updated
PhoenixHu/grpo_internvl2_5_how2sign_1b_bleu1_bleu4_checkpoint31656_newalldata_lora16_0517
Updated
PhoenixHu/grpo_internvl2_5_how2sign_1b_bleu1_bleu4_checkpoint31656_newalldata_lora16_moredata_0523
Updated
PhoenixHu/grpo_internvl2_5_how2sign_1b_bleu1_bleu4_checkpoint31656_newalldata_lora16_12kdata_0523
Updated