AI & ML interests
None yet
Organizations
None yet
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k_grpo_gaussian_0_75_0_25_True_400
Text Generation
• 2B • Updated • 3
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k_grpo_cosine_0_5_0_5_True_1600
Text Generation
• 2B • Updated • 5
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k_grpo_gaussian_0_25_0_75_True_1600
Text Generation
• 2B • Updated • 11
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k_grpo_gaussian_0_5_0_5_True_1600
Text Generation
• 2B • Updated • 7
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k_grpo_balanced_0_5_0_5_True_1600
Text Generation
• 2B • Updated • 5
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k2_grpo_gaussian_0_5_0_5_True_1600
Text Generation
• 2B • Updated • 7
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k_grpo_cosine_0_5_0_5_True_400
Updated
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k_grpo_balanced_0_5_0_5_True_400
Updated
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k2_grpo_cosine_0_5_0_5_True_1600
Updated
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k_grpo_balanced_0_5_0_5_True_1200
Text Generation
• 2B • Updated • 9
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k_grpo_cosine_0_5_0_5_True_1200
Text Generation
• 2B • Updated • 6
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k_grpo_gaussian_0_5_0_5_True_1200
Text Generation
• 2B • Updated • 10
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k2_grpo_gaussian_0_5_0_5_True_1200
Text Generation
• 2B • Updated • 8
blakeaolson/Qwen2.5-1.5B-Instruct_easymath_grpo_gaussian_0_5_0_5_True_1200
Updated
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k2_grpo_balanced_0_5_0_5_True_1200
Updated
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k2_grpo_cosine_0_5_0_5_True_1200
Updated
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k_sgrpo_balanced_0_5_0_5_True_300
Text Generation
• 2B • Updated • 9
blakeaolson/Qwen2.5-3B-Instruct_countdown4_sgrpo_cosine_0_5_0_5_True_300
Updated
blakeaolson/Qwen2.5-1.5B-Instruct_gsm8k_sgrpo_cosine_0_5_0_5_True_300
Updated
blakeaolson/Qwen2.5-3B-Instruct_countdown4_grpo_balanced_0_5_0_5_True_1200
Updated
blakeaolson/Qwen2.5-3B-Instruct_gsm8k_grpo_balanced_0_5_0_5_True_1200
Updated