zwt123home123/code_log_3
Updated
Wentian Zhao
zwt123home123
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
5 days ago
Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified
Self-Play
upvoted
a
paper
7 days ago
EPO: Entropy-regularized Policy Optimization for LLM Agents
Reinforcement Learning
upvoted
a
paper
3 months ago
Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs
Organizations
None yet
zwt123home123/reproduce_log
Updated
zwt123home123/code_log_2
Updated
zwt123home123/standardtraining_2p_Qwen2.5-7B-Instruct-1M-4ppl_largebs_global_step_320_actor
8B
•
Updated
•
2
zwt123home123/standardtraining_2p_Qwen2.5-7B-Instruct-1M-4ppl_largebs_global_step_203_actor
8B
•
Updated
•
3
zwt123home123/standardtraining_2p_Qwen2.5-7B-Instruct-1M-3ppl_largebs_global_step_203_actor
8B
•
Updated
zwt123home123/standardtraining_2p_Qwen2.5-7B-Instruct-1M-3ppl_largebs_global_step_400_actor
8B
•
Updated
•
1
zwt123home123/global_step_840_actor
8B
•
Updated
•
2
zwt123home123/InternVL2_5-8B
Image-Text-to-Text
•
8B
•
Updated
zwt123home123/KV_internvl26b
Updated
zwt123home123/13b_LUT_c100_zpz5_afterrope_nonorm_group_v_cache_640
Updated
zwt123home123/13b_LUT_c100_zpz5_prerope_nonorm_group_v_cache_640
Updated
zwt123home123/attn_weights_save_7b_all_layers_concat_10
Updated
zwt123home123/attn_weights_save_7b_all_layers_concat
Updated
zwt123home123/attn_weights_save_7b_all_layers
Updated
zwt123home123/13b_K_LUT_c1k_d1m_prerope
Updated
zwt123home123/13b_K_LUT_c10k_d1m_prerope
Updated
zwt123home123/7b_V_cache_512_reuse_zp28
Updated
zwt123home123/13b_K_LUT_c10_d1m_prerope
Updated
zwt123home123/13b_K_LUT_c2_d1m_prerope
Updated
zwt123home123/13b_K_LUT_c100_d1m_prerope
Updated
zwt123home123/13b_K_LUT_c10k
Updated
zwt123home123/weights_group_320_K
Updated
zwt123home123/13b_V_cache_320_group
Updated
zwt123home123/13b_V_cache_640_group
Updated
zwt123home123/13b_V_cache_1280_group
Updated
zwt123home123/weights_group_1280
Updated
zwt123home123/13b_V_cache_480
Updated
zwt123home123/13b_V_cache_320
Updated
zwt123home123/13b_V_cache_80
Updated