QinLiuNLP/llama3-sudo-5epochs-tofu_full_sft download history
QinLiuNLP/llama3-sudo-5epochs-tofu_full_sft is an 8.0B-parameter model by QinLiuNLP. In the last 30 days it was downloaded 6 times (3 in the last 7 days), and 309 times in total.
It ranks #928,869 on the Hub by monthly downloads.
It has 0 likes.
It is a fine-tune of meta-llama/Meta-Llama-3-8B-Instruct.
16 models build on llama3-sudo-5epochs-tofu_full_sft: 0 quantized, 9 fine-tuned, 7 adapters and 0 merges. Together with the original they were downloaded 69 times in the last 30 days. See the llama3-sudo-5epochs-tofu_full_sft galaxy.
Most downloaded derivatives
- QinLiuNLP/llama3-sudo-dpo-5epochs-forget10mix400-1sft-2fullpara-2e-4 (finetune), 11 downloads in 30 days
- QinLiuNLP/llama3-sudo-dpo-3epochs-forget10mix400-1sft-2fullpara (finetune), 6 downloads in 30 days
- QinLiuNLP/llama3-sudo-dpo-instruct-5epochs-forget10-fullpara (finetune), 6 downloads in 30 days
- QinLiuNLP/llama3-sudo-dpo-5epochs-forget10mix400-1sft-2fullpara (finetune), 5 downloads in 30 days
- QinLiuNLP/llama3-sudo-dpo-5epochs-forget10mix400-1sft-2fullpara-1e-5 (finetune), 5 downloads in 30 days
- QinLiuNLP/llama3-sudo-dpo-instruct-5epochs-forget10-lora (adapter), 5 downloads in 30 days
- QinLiuNLP/llama3-sudo-dpo-10epochs-forget10mix400-1sft-2fullpara-1e-5 (finetune), 4 downloads in 30 days
- QinLiuNLP/llama3-sudo-dpo-5epochs-forget10mixall-1sft-2fullpara-1e-5 (finetune), 4 downloads in 30 days
- QinLiuNLP/llama3-sudo-dpo-10epochs-forget10mixall-1sft-2fullpara-1e-5 (finetune), 3 downloads in 30 days
- QinLiuNLP/llama3-sudo-dpo-5epochs-forget10mix-1sft-2lora (adapter), 3 downloads in 30 days
- QinLiuNLP/llama3-sudo-dpo-instruct-10epochs-forget10-1sft-2lora (adapter), 3 downloads in 30 days
- QinLiuNLP/llama3-sudo-dpo-10epochs-forget10mixall-1sft-2lora-1e-5 (adapter), 2 downloads in 30 days
Open QinLiuNLP/llama3-sudo-5epochs-tofu_full_sft on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.