The RLHFlow/LLaMA3-SFT-v2 galaxy
22 models are built on RLHFlow/LLaMA3-SFT-v2: 4 quantized, 6 fine-tuned, 12 adapters and 0 merges. Together they were downloaded 2,572 times in the last 30 days.
Most downloaded direct derivatives
- featherless-ai-quants/RLHFlow-LLaMA3-SFT-v2-GGUF (quantized), 765 downloads in 30 days
- mradermacher/LLaMA3-SFT-v2-i1-GGUF (quantized), 704 downloads in 30 days
- mradermacher/LLaMA3-SFT-v2-GGUF (quantized), 257 downloads in 30 days
- tensorblock/LLaMA3-SFT-v2-GGUF (quantized), 121 downloads in 30 days
- yyqoni/rlhflow-llama-3-sft-8b-v2-token-rm-700k (finetune), 22 downloads in 30 days
- yyqoni/rlhflow-llama-3-sft-8b-v2-bandit-ppo-60k (finetune), 18 downloads in 30 days
- yyqoni/rlhflow-llama-3-sft-8b-v2-segment-ppo-60k (finetune), 18 downloads in 30 days
- yyqoni/rlhflow-llama-3-sft-8b-v2-token-ppo-60k (finetune), 15 downloads in 30 days
- ducthang1703/llama3-8b-arc-bpo-lora-noise20-smoke-128 (adapter), 9 downloads in 30 days
- ducthang1703/llama3-arc-bpo-lora-1k (adapter), 9 downloads in 30 days
- ducthang1703/llama3-arc-bpo-uniform-1k (adapter), 9 downloads in 30 days
- ducthang1703/llama3-arc-bpo-uniform-lora-full-bs64 (adapter), 9 downloads in 30 days
- ducthang1703/llama3-8b-arc-bpo-lora-noise20-16k (adapter), 8 downloads in 30 days
- ducthang1703/llama3-arc-bpo-uniform-lora-10k-bs64 (adapter), 8 downloads in 30 days
- ducthang1703/llama3-arc-bpo-uniform-lora-1k-test (adapter), 8 downloads in 30 days
- yyqoni/rlhflow-llama-3-sft-8b-v2-segment-rm-700k (finetune), 8 downloads in 30 days
- ducthang1703/llama3-arc-bpo-adv-lora-1k (adapter), 7 downloads in 30 days
- ducthang1703/llama-arc-bpo-uniform-lora-smoke-64 (adapter), 5 downloads in 30 days
- ducthang1703/llama3-8b-arc-bpo-lora-noise10-16k (adapter), 5 downloads in 30 days
- ducthang1703/llama3-arc-bpo-lora-smoke-64 (adapter), 5 downloads in 30 days
- ducthang1703/llama3-arc-bpo-uniform-lora-smoke64 (adapter), 5 downloads in 30 days
- hohieuresearch/project-hdhodp1 (finetune), 0 downloads in 30 days