The shuoxing/llama3-8b-full-pretrain-mix-high-tweet-1m-en-no-packing-new galaxy

1 models are built on shuoxing/llama3-8b-full-pretrain-mix-high-tweet-1m-en-no-packing-new: 0 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 34 times in the last 30 days.

Most downloaded direct derivatives

• shuoxing/llama3-8b-full-pretrain-mix-high-tweet-1m-en-no-packing-new-sft-bs128 (finetune), 12 downloads in 30 days

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.