The elyza/ELYZA-japanese-Llama-2-7b-fast galaxy

3 models are built on elyza/ELYZA-japanese-Llama-2-7b-fast: 2 quantized, 0 fine-tuned, 0 adapters and 1 merges. Together they were downloaded 1,182 times in the last 30 days.

Most downloaded direct derivatives

• Aratako/ELYZA-japanese-Llama-2-fast-MoE-2x7B-v0.1 (merge), 231 downloads in 30 days
• tensorblock/elyza_ELYZA-japanese-Llama-2-7b-fast-GGUF (quantized), 67 downloads in 30 days

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