The OpenRLHF/Llama-3-8b-sft-mixture galaxy
19 models are built on OpenRLHF/Llama-3-8b-sft-mixture: 9 quantized, 10 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 3,142 times in the last 30 days.
Most downloaded direct derivatives
- featherless-ai-quants/OpenRLHF-Llama-3-8b-sft-mixture-GGUF (quantized), 400 downloads in 30 days
- tensorblock/Llama-3-8b-sft-mixture-GGUF (quantized), 71 downloads in 30 days
- RTO-RL/Llama3-8B-DPO (finetune), 12 downloads in 30 days
- anonymous4submission/Llama3-8B-IDRM (finetune), 11 downloads in 30 days
- RTO-RL/Llama3-8B-RewardModel (finetune), 10 downloads in 30 days
- RTO-RL/Llama3-8B-RTO (finetune), 8 downloads in 30 days
- RTO-RL/Llama3-8B-RPP (finetune), 7 downloads in 30 days
- RTO-RL/Llama3-8B-TDPO (finetune), 7 downloads in 30 days
- RTO-RL/Llama3-8B-PPO (finetune), 6 downloads in 30 days
- RTO-RL/Llama3-8B-RDPO (finetune), 6 downloads in 30 days
- RTO-RL/Llama3-8B-RTO_RPP (finetune), 3 downloads in 30 days
- RTO-RL/Llama3-8B-SimPO (finetune), 2 downloads in 30 days