Introducing Gemma with a 10M context window
We feature:
• 1250x context length of base Gemma
• Requires less than 32GB of memory
• Infini-attention + activation compression
Check us out on:
• 🤗: https://t.co/njkPIVSBFh
• GitHub: https://t.co/ZhcFvN0IW0
• Technical blog: https://t.co/dPRfwMDuil
Built by: @maxaljadery, @AkshGarg03, @siddrrsh