Article
5
Zhaolin Gao
GitBag
AI & ML interests
Reinforcement Learning from Human Feedback
Recent Activity
updated
a dataset
13 days ago
GitBag/math_qwen3_1.7B_8192_n_128_eval_len
published
a dataset
13 days ago
GitBag/math_qwen3_1.7B_8192_n_128_eval_len
updated
a dataset
13 days ago
GitBag/math_qwen2.5_3B_8192_n_128_eval_len
Organizations
models
328
GitBag/a_star_final_a_star_math_1.5_random_reward_actor
Text Generation
•
2B
•
Updated
•
27
GitBag/a_star_final_a_star_math_1.5_wrong_reward_actor
Text Generation
•
2B
•
Updated
•
24
GitBag/a_star_final_a_star_math_3_wrong_reward_actor
Text Generation
•
3B
•
Updated
•
56
GitBag/a_star_final_a_star_math_3_random_reward_actor
Text Generation
•
3B
•
Updated
•
25
GitBag/a_star_final_a_star_math_7_wrong_reward_actor
Text Generation
•
8B
•
Updated
•
54
GitBag/a_star_final_a_star_math_7_random_reward_actor
Text Generation
•
8B
•
Updated
•
62
GitBag/a_star_final_ds-distilled-qwen-1.5b-a-star-16384_actor
Text Generation
•
2B
•
Updated
•
9
GitBag/a_star_final_ds-distilled-qwen-1.5b-grpo-2-kl-1e-4-16384_actor
Text Generation
•
2B
•
Updated
•
26
GitBag/a_star_final_ds-distilled-qwen-1.5b-ppo-kl-1e-4-ec-0.001-16384_critic
Token Classification
•
2B
•
Updated
•
6
GitBag/a_star_final_ds-distilled-qwen-1.5b-ppo-kl-1e-4-ec-0.001-16384_actor
Text Generation
•
2B
•
Updated
•
40
datasets
467
GitBag/math_qwen3_1.7B_8192_n_128_eval_len
Viewer
•
Updated
•
7.5k
•
82
GitBag/math_qwen2.5_3B_8192_n_128_eval_len
Viewer
•
Updated
•
7.5k
•
80
GitBag/math_qwen2.5_1.5B_8192_n_128_eval_len
Viewer
•
Updated
•
7.5k
•
93
GitBag/math_qwen3_4B_8192_n_128_eval_len
Viewer
•
Updated
•
7.5k
•
85
GitBag/math_qwen2.5_7B_8192_n_128_eval_len
Viewer
•
Updated
•
7.5k
•
84
GitBag/math_qwen3_8B_8192_n_128_eval_len
Viewer
•
Updated
•
7.5k
•
86
GitBag/math_qwen2.5_1.5B_8192_n_128_eval
Viewer
•
Updated
•
7.5k
•
80
GitBag/math_qwen3_1.7B_8192_n_128_eval
Viewer
•
Updated
•
7.5k
•
82
GitBag/math_qwen2.5_3B_8192_n_128_eval
Viewer
•
Updated
•
7.5k
•
82
GitBag/math_qwen3_4B_8192_n_128_eval
Viewer
•
Updated
•
7.5k
•
87