The W-61/llama-3-8b-base-sft-ultrachat-8xh200 galaxy
68 models are built on W-61/llama-3-8b-base-sft-ultrachat-8xh200: 0 quantized, 68 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 807 times in the last 30 days.
Most downloaded direct derivatives
- W-61/llama-3-8b-base-margin-dpo-ultrafeedback-8xh200 (finetune), 17 downloads in 30 days
- jackf857/llama-3-8b-base-cpo-ultrafeedback-4xH200-batch-128-rerun (finetune), 17 downloads in 30 days
- jackf857/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.4-s_star-0.5 (finetune), 17 downloads in 30 days
- W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.4-s_star-0.2-20260426-185938 (finetune), 16 downloads in 30 days
- W-61/llama3-8b-base-new-method-q_t-0.4-s_star0.6-beta-next-batch (finetune), 16 downloads in 30 days
- jackf857/llama-3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260428-035521 (finetune), 16 downloads in 30 days
- W-61/b200-l3-ultra-schsel-lin-s1001-v1-a2 (finetune), 15 downloads in 30 days
- jackf857/llama-3-8b-base-r-dpo-ultrafeedback-4xH200-batch-128-rerun-2-runpod (finetune), 15 downloads in 30 days
- jackf857/llama-3-8b-base-orpo-ultrafeedback-4xh200-rerun (finetune), 14 downloads in 30 days
- W-61/llama-3-8b-base-beta-dpo-ultrafeedback-8xh200 (finetune), 14 downloads in 30 days
- jackf857/llama-3-8b-base-ipo-ultrafeedback-4xh200-batch-128-rerun-2-runpod (finetune), 14 downloads in 30 days
- jackf857/llama-3-8b-base-kto-ultrafeedback-8xh200 (finetune), 14 downloads in 30 days
- W-61/b200-l3-ultra-sel-lsc-qt45-z35-s1001-v1-a3 (finetune), 14 downloads in 30 days
- W-61/b200-l3-ultra-bsw-lsc-b0p05-s42-v1-a1 (finetune), 13 downloads in 30 days
- W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124 (finetune), 13 downloads in 30 days
- W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.3-20260428-045924 (finetune), 13 downloads in 30 days
- W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-s_star-0.4-20260425-111846 (finetune), 13 downloads in 30 days
- W-61/llama3-8b-base-new-method-s_star0.6-20260426-230653 (finetune), 13 downloads in 30 days
- W-61/lsc-dpo-phase4-readiness-preflight-3ee9002 (finetune), 13 downloads in 30 days
- jackf857/llama-3-8b-base-ipo-ultrafeedback-4xh200-batch-128-20260428-004616 (finetune), 13 downloads in 30 days
- jackf857/llama-3-8b-base-ipo-ultrafeedback-4xh200-batch-128-rerun (finetune), 13 downloads in 30 days
- jackf857/llama-3-8b-base-ipo-ultrafeedback-8xh200 (finetune), 13 downloads in 30 days
- jackf857/llama-3-8b-base-robust-dpo-ultrafeedback-8xh200 (finetune), 13 downloads in 30 days
- W-61/b200-l3-ultra-bsw-dpo-b0p1-s42-v1-a1 (finetune), 12 downloads in 30 days
- W-61/b200-l3-ultra-conf-dpo-s44-v1-a2 (finetune), 12 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.