mlfoundations-dev/qwen2-5_multiple_samples_ground_truth_openr1_llm_verifier_clean Text Generation • 0.5B • Updated Mar 16 • 5
mlfoundations-dev/DCFT-pos_neg_ablation_instruction_filtering_seed_math_best_s1-etash 8B • Updated Mar 16 • 1
mlfoundations-dev/DCFT-pos_neg_ablation_instruction_filtering_seed_math_baseline-etash 8B • Updated Mar 16 • 1
mlfoundations-dev/global_batchsize_512_lradjusted8_constant Text Generation • 8B • Updated Mar 15 • 5
mlfoundations-dev/DCFT-pos_neg_ablation_instruction_filtering_seed_math_worst_mix_3_1-etash 8B • Updated Mar 15 • 1
mlfoundations-dev/DCFT-pos_neg_ablation_instruction_filtering_seed_math_best_tigerlab-etash 8B • Updated Mar 15 • 2
mlfoundations-dev/DCFT-pos_neg_ablation_instruction_filtering_seed_code_worst_1-etash 8B • Updated Mar 15 • 1
mlfoundations-dev/DCFT-instruction_filtering_scale_up_code_base_random_filtering_8K-etash 8B • Updated Mar 15 • 1