Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_spell_backward_3_10_noise_btw_7_8_0p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
37
KazukiEgashira
Kazuki1450
AI & ML interests
None yet
Recent Activity
updated
a model
1 day ago
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_spell_backward_3_10_noise_btw_7_8_0p0_1p0_1p0_grpo_42_targeted
published
a model
1 day ago
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_spell_backward_3_10_noise_btw_7_8_0p0_1p0_1p0_grpo_42_targeted
updated
a model
2 days ago
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_spell_backward_len_3_10_noiselen_leq_5_0p0_1p0_1p0_grpo_42_targeted
Organizations
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_spell_backward_len_3_10_noiselen_leq_5_0p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
48
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_spell_backward_len_3_10_leven_1_1p0_0p5_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
70
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_spell_backward_len_3_10_leven_1_0p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
59
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_spell_backward_len_3_10_leven_1_1p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
65
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_spell_backward_len_3_10_1p0_1p0_1p0_grpo_42_uniform
Updated
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_spell_backward_len_3_10_1p0_0p0_1p0_grpo_42_uniform
Text Generation
•
2B
•
Updated
•
8
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_chain_sum_2048_1p0_0p0_1p0_grpo_42_uniform
Text Generation
•
2B
•
Updated
•
37
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_chain_sum_correct_run_1p0_0p0_1p0_grpo_42_uniform
Updated
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_chain_sum_1p0_0p0_1p0_grpo_42_uniform
Text Generation
•
2B
•
Updated
•
57
Kazuki1450/Qwen2.5-1.5B-Instruct_rgym_chain_sum_1p0_0p0_1p0_grpo_42_targeted
Updated
Kazuki1450/Qwen2.5-1.5B-Instruct_lightr1_stage1_1p0_0p0_1p0_grpo_42_uniform
Text Generation
•
2B
•
Updated
•
113
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_relerr0.1_0p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
14
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_relerr0.1_1p0_0p5_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
10
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_relerr0.1_1p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
14
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_6_15_6_15_flip_format_0p5_0p5_1p0_grpo_42_format
Text Generation
•
2B
•
Updated
•
60
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_relerr10_0p5_0p5_1p0_grpo_42_targeted
Updated
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_1p0_1p0_1p0_grpo_42_format
Text Generation
•
2B
•
Updated
•
12
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_6_15_6_15_flip_format_1p0_1p0_1p0_grpo_42_format
Updated
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_relerr10_1p0_0p0_1p0_grpo_42_targeted
Updated
Kazuki1450/Qwen3-1.7B_rgym_chain_sum_relerr10_1p0_0p0_1p0_grpo_42_targeted
Updated
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_6_15_6_15_flip_terms_eq_15_0p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
50
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_6_15_6_15_flip_terms_eq_6_0p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
47
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_6_15_6_15_flip_terms_leq_10_0p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
38
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_6_15_6_15_flip_terms_eq_10_0p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
42
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_6_15_6_15_flip_terms_geq_11_0p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
42
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_6_15_6_15_terms_geq_11_1p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
44
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_6_15_6_15_terms_leq_10_1p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
38
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_6_15_6_15_terms_eq_15_1p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
51
Kazuki1450/Qwen3-1.7B-Base_rgym_chain_sum_6_15_6_15_terms_eq_10_1p0_1p0_1p0_grpo_42_targeted
Text Generation
•
2B
•
Updated
•
3