The stage-babylm/llama-256-12L galaxy

2 models are built on stage-babylm/llama-256-12L: 0 quantized, 2 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 263 times in the last 30 days.

Most downloaded direct derivatives

• stage-babylm/llama-256-12L-qa (finetune), 66 downloads in 30 days
• NoeMastro/qa-finetune (finetune), 59 downloads in 30 days

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