The Trelis/Llama-2-7b-chat-hf-hosted-inference-8bit galaxy

1 models are built on Trelis/Llama-2-7b-chat-hf-hosted-inference-8bit: 0 quantized, 0 fine-tuned, 1 adapters and 0 merges. Together they were downloaded 36 times in the last 30 days.

Most downloaded direct derivatives

• linuscarey123/llama2-ca-prequant (adapter), 6 downloads in 30 days

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