rediska0123/qwen2.5-math-1.5b-dpo-gsm8k
Text Generation • 2B • Updated
• 40
Ekaterina Fadeeva
rediska0123
AI & ML interests
None yet
Recent Activity
updated
a dataset about 1 hour ago
rediska0123/gsm8k_dpo_pairs updated
a model about 6 hours ago
rediska0123/qwen2.5-math-1.5b-dpo-gsm8k-v3 updated
a model about 6 hours ago
rediska0123/qwen2.5-math-1.5b-dpo-gsm8k-v2 Organizations
models 264
rediska0123/qwen2.5-math-1.5b-dpo-gsm8k-v3
Text Generation • 2B • Updated
rediska0123/qwen2.5-math-1.5b-dpo-gsm8k-v2
Text Generation • 2B • Updated
rediska0123/qwen2.5-math-1.5b-dpo-gsm8k-3epochs
Text Generation • 2B • Updated
rediska0123/qwen2.5-math-1.5b-dpo-gsm8k-2epochs
Text Generation • 2B • Updated
rediska0123/qwen2.5-math-1.5b-dpo-gsm8k-1epoch
Text Generation • 2B • Updated
rediska0123/uhead_Qwen2.5-1.5B-Instruct_random_weights
Updated
• 16
rediska0123/uhead_Qwen2.5-7B-Instruct_prm12k_15epochs
Updated
• 168
rediska0123/uhead_Qwen2.5-7B-Instruct_prm12k_10epochs
Updated
• 268
rediska0123/ue_manager_trip_uhead_token_Qwen3-8B_fixed_prm_feature_linear_hs_20e_best_at_epoch7
Updated
datasets 117
rediska0123/gsm8k_dpo_pairs
Viewer
• Updated
• 654
rediska0123/train_math-from-prm800k_Qwen2.5-7B_joint_prompts
Viewer
• Updated
• 11.4k • 26
rediska0123/train_math-from-prm800k_mathprompt_Qwen2.5-7B
Viewer
• Updated
• 2.4k • 25
rediska0123/train_math-from-prm800k_Qwen2.5-7B
Viewer
• Updated
• 9k • 44
rediska0123/test_trip_qwen3_thinking
Viewer
• Updated
• 500 • 6
rediska0123/test_calendar_qwen3_thinking
Viewer
• Updated
• 500 • 7
rediska0123/test_meet_qwen3_thinking
Viewer
• Updated
• 500 • 7
rediska0123/test_sciqa_qwen3_thinking
Viewer
• Updated
• 500 • 7
rediska0123/test_stqa_qwen3_thinking
Viewer
• Updated
• 500 • 7
rediska0123/test_proofnet_large_qwen3_thinking
Viewer
• Updated
• 371 • 6