·
AI & ML interests
LLMs
Recent Activity
Organizations
None yet
ZHLiu627/warm_start_sft_v2
Preview
• Updated
• 5
ZHLiu627/sciworld_dataset
Preview
• Updated
• 10
ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v1
Viewer
• Updated
• 29.3k • 5
ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filtered_v1_v1
Viewer
• Updated
• 29.3k • 5
• 1
ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filtered_v1
Viewer
• Updated
• 29.3k • 5
ZHLiu627/updated-code-qwen7-edufiltered
Viewer
• Updated
• 43k • 4
ZHLiu627/updated-code-qwen7-edu
Viewer
• Updated
• 75.6k • 10
ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v2filtered
Viewer
• Updated
• 28.9k • 3
ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v2
Viewer
• Updated
• 29.3k • 5
ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filteredd
Viewer
• Updated
• 29.3k • 3
ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v1filtered
Viewer
• Updated
• 29.1k • 3
ZHLiu627/qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v2
Viewer
• Updated
• 29.3k • 3
ZHLiu627/qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v1
Viewer
• Updated
• 29.3k • 3
Viewer
• Updated
• 118k • 4
ZHLiu627/ultrafeedback_binarized_with_response_full
Viewer
• Updated
• 61.1k • 6
ZHLiu627/ultrafeedback_binarized_with_response_full_part2
Viewer
• Updated
• 21.1k • 4
ZHLiu627/ultrafeedback_binarized_with_response_full_part1
Viewer
• Updated
• 20k • 6
• 1
ZHLiu627/ultrafeedback_binarized_with_response_full_part0
Viewer
• Updated
• 20k • 4
