Auto-formalized versions of GSM8K and MATH500 auto-formalized and filtered with Goedel models
Ujan PRO
Ujan
·
AI & ML interests
NLP, Speech
Recent Activity
updated a dataset about 12 hours ago
Ujan/math500_formal_eval_Phi-4-mini-reasoning_prover_judge published a dataset about 12 hours ago
Ujan/math500_formal_eval_Phi-4-mini-reasoning_prover_judge updated a dataset about 13 hours ago
Ujan/math500_formal_eval_gemma-4-E4B-it_prover_judgeOrganizations
Formal v1
Auto-formalized versions of GSM8K with the state-of-the-art Goedel-Prover-V2 and filtered using Deepseek-Prover-V2
-
Ujan/gsm8k_formal_goedel_few_shot_filtered_Goedel-Prover-V2-32B
Viewer • Updated • 1.18k • 34 -
Ujan/gsm8k_formal_goedel_zero_shot_filtered_DeepSeek-Prover-V2-7B
Viewer • Updated • 1.15k • 37 -
Ujan/gsm8k_formal_goedel_zero_shot_filtered_Goedel-Prover-V2-32B
Viewer • Updated • 1.23k • 9 -
Ujan/gsm8k_formal_goedel_few_shot
Viewer • Updated • 1.3k • 7
Formal v2
Auto-formalized versions of GSM8K and MATH500 auto-formalized and filtered with Goedel models
Formal v1
Auto-formalized versions of GSM8K with the state-of-the-art Goedel-Prover-V2 and filtered using Deepseek-Prover-V2
-
Ujan/gsm8k_formal_goedel_few_shot_filtered_Goedel-Prover-V2-32B
Viewer • Updated • 1.18k • 34 -
Ujan/gsm8k_formal_goedel_zero_shot_filtered_DeepSeek-Prover-V2-7B
Viewer • Updated • 1.15k • 37 -
Ujan/gsm8k_formal_goedel_zero_shot_filtered_Goedel-Prover-V2-32B
Viewer • Updated • 1.23k • 9 -
Ujan/gsm8k_formal_goedel_few_shot
Viewer • Updated • 1.3k • 7
models 8
Ujan/Qwen3-4B-Base_DeepMath-103K_samples_10000_seq_2048_epoch_1
Text Generation • 4B • Updated • 2 •
Ujan/Qwen3-4B-Base_DeepMath-103K_samples_50000_seq_16384_epoch_1
Text Generation • 4B • Updated • 1
Ujan/Qwen3-4B-Base_DeepMath-103K_samples_50000_seq_8192_epoch_1
Text Generation • 4B • Updated • 4
Ujan/Qwen3-4B-Base_DeepMath-103K_samples_50000_seq_4096_epoch_1
Text Generation • 4B • Updated • 3
Ujan/Qwen3-4B-Base_DeepMath-103K_samples_10000_seq_16384_epoch_1
Text Generation • 4B • Updated • 1
Ujan/Qwen3-4B-Base_DeepMath-103K_samples_10000_seq_4096_epoch_1
Text Generation • 4B • Updated • 2 •
Ujan/Qwen3-4B-Base_DeepMath-103K_samples_10000_seq_8192_epoch_1
Text Generation • 4B • Updated • 2
Ujan/whisper-small_moe_k_means
Automatic Speech Recognition • Updated • 5
datasets 96
Ujan/math500_formal_eval_Phi-4-mini-reasoning_prover_judge
Viewer • Updated • 1
Ujan/math500_formal_eval_gemma-4-E4B-it_prover_judge
Viewer • Updated • 42
Ujan/math500_formal_eval_Phi-4-mini-reasoning_prover
Viewer • Updated • 6 • 1
Ujan/math500_formal_eval_gemma-4-E4B-it_prover
Viewer • Updated • 70
Ujan/math500_formal_eval_Phi-4-mini-reasoning
Viewer • Updated • 8
Ujan/math500_formal_eval_granite-4.1-8b_prover_judge
Viewer • Updated • 41
Ujan/math500_formal_eval_gemma-4-E4B-it
Viewer • Updated • 106
Ujan/math500_formal_eval_granite-4.1-8b_prover
Viewer • Updated • 49
Ujan/math500_formal_eval_granite-4.1-8b
Viewer • Updated • 85
Ujan/math500_formal_eval_Falcon-H1R-7B_prover_judge
Viewer • Updated • 82 • 12