The geodesic-research/sfm_filtered_midtrain_alignment_upsampled_instruct galaxy

1 models are built on geodesic-research/sfm_filtered_midtrain_alignment_upsampled_instruct: 0 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 29 times in the last 30 days.

Most downloaded direct derivatives

• camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_synth_align_mid-DPO (finetune), 7 downloads in 30 days