mlfoundations-dev/DCFT-pos_neg_ablation_instruction_filtering_seed_code_best_ioi-etash
8B • Updated • 1
mlfoundations-dev/DCFT-pos_neg_ablation_instruction_filtering_seed_code_best_codegolf-etash
8B • Updated mlfoundations-dev/DCFT-pos_neg_ablation_instruction_filtering_seed_code_best_codeforces-etash
8B • Updated mlfoundations-dev/global_batchsize_512_lradjusted32
Text Generation
• 8B • Updated • 1
mlfoundations-dev/2k_chunk_general-thought-feb-25
Text Generation
• 8B • Updated mlfoundations-dev/DCFT-pos_neg_ablation_instruction_filtering_seed_code_best_mix-etash
8B • Updated • 1
mlfoundations-dev/DCFT-pos_neg_ablation_instruction_filtering_seed_code_best_codefeedback-etash
8B • Updated • 1
mlfoundations-dev/reasoning_hp_ablations_bsz128_laradjusted
Text Generation
• 8B • Updated • 21
mlfoundations-dev/reasoning_hp_ablations_bsz256_lradjusted
Text Generation
• 8B • Updated mlfoundations-dev/reasoning_hp_ablations_bsz512_lradjusted
Text Generation
• 8B • Updated • 1
mlfoundations-dev/herorun_1_1
Text Generation
• 8B • Updated • 1
mlfoundations-dev/DCFT-scale_up_science_8K-etash
8B • Updated • 1
mlfoundations-dev/DCFT-scale_up_science_4K-etash
8B • Updated • 1
mlfoundations-dev/DCFT-scale_up_science_2K-etash
8B • Updated • 1
mlfoundations-dev/DCFT-scale_up_science_1K-etash
8B • Updated • 1
mlfoundations-dev/DCFT-scale_up_science_16K-etash
8B • Updated • 1
mlfoundations-dev/deepspeed_no_offload_liger_torchcompile
Text Generation
• 8B • Updated • 1
mlfoundations-dev/deepspeed_no_offload_liger
Text Generation
• 8B • Updated mlfoundations-dev/deepspeed_no_offload
Text Generation
• 8B • Updated • 1
mlfoundations-dev/training_baseline
Text Generation
• 8B • Updated • 2
mlfoundations-dev/sci_question_exp__scp_116k__training_2k_for_GPQA
Text Generation
• 8B • Updated • 2
mlfoundations-dev/DCFT-seed_code_multiple_gpt_verification-etash
8B • Updated • 1
mlfoundations-dev/SCP_40k_R1_with_OT_verified__100_samples
Text Generation
• 8B • Updated • 3
mlfoundations-dev/SCP_40k_R1_with_OT_verified__1_samples
Text Generation
• 8B • Updated • 1
mlfoundations-dev/liger_test
Text Generation
• 8B • Updated • 1
mlfoundations-dev/dedup_ablation_sim_threshold_40
Text Generation
• 8B • Updated mlfoundations-dev/multiple_samples_all_openr1_clean
Text Generation
• 8B • Updated mlfoundations-dev/1epoch_extra_unverified
Text Generation
• 8B • Updated mlfoundations-dev/1epoch_extra_verified
Text Generation
• 8B • Updated mlfoundations-dev/1epoch_stratos_unverified_mix
Text Generation
• 8B • Updated • 1