ZHLiu627/zephyr-7b-gemma-rpo-avg
Updated
•
40
Zhihan Liu
ZHLiu627
AI & ML interests
LLMs
Recent Activity
upvoted
a
paper
12 days ago
Self-rewarding correction for mathematical reasoning
updated
a dataset
12 days ago
ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v1
updated
a dataset
12 days ago
ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filtered_v1_v1
Organizations
None yet
models
7
ZHLiu627/beta_ultra_rdpo_full_eta0.005_beta0.01_no_decay_new
Updated
•
10
ZHLiu627/debug
Updated
•
8
ZHLiu627/zephyr-7b-gemma-dpo
Updated
•
3
ZHLiu627/zephyr-gemma-rpo
Text Generation
•
Updated
•
11
ZHLiu627/zephyr-7b-dpo-full
Text Generation
•
Updated
•
18
ZHLiu627/zephyr-7b-rdpo-full-eta0.005-beta0.1
Updated
datasets
16
ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v1
Viewer
•
Updated
•
29.3k
•
65
ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filtered_v1_v1
Viewer
•
Updated
•
29.3k
•
40
ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filtered_v1
Viewer
•
Updated
•
29.3k
•
210
ZHLiu627/updated-code-qwen7-edufiltered
Viewer
•
Updated
•
43k
•
49
ZHLiu627/updated-code-qwen7-edu
Viewer
•
Updated
•
75.6k
•
47
ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v2filtered
Viewer
•
Updated
•
28.9k
•
55
ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v2
Viewer
•
Updated
•
29.3k
•
42
ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filteredd
Viewer
•
Updated
•
29.3k
•
48
ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v1filtered
Viewer
•
Updated
•
29.1k
•
48
ZHLiu627/qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v2
Viewer
•
Updated
•
29.3k
•
61