The wang7776/Llama-2-7b-chat-hf-30-attention-sparsity galaxy

1 models are built on wang7776/Llama-2-7b-chat-hf-30-attention-sparsity: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 394 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/Llama-2-7b-chat-hf-30-attention-sparsity-GGUF (quantized), 332 downloads in 30 days

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