The wang7776/Mistral-7B-Instruct-v0.2-attention-sparsity-20 galaxy

1 models are built on wang7776/Mistral-7B-Instruct-v0.2-attention-sparsity-20: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 389 times in the last 30 days.

Most downloaded direct derivatives

• featherless-ai-quants/wang7776-Mistral-7B-Instruct-v0.2-attention-sparsity-20-GGUF (quantized), 334 downloads in 30 days

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