Open evgenyigumnov opened 1 month ago
This should now be available and the default when using the gemma example!
Thanks a lot! But what about quntinezed mode ? https://github.com/huggingface/candle/issues/2450
gemma2:2b quntinezed version have 1.5Gb size! This is amaziong and high quelity!
Hello Sir and Madam,
Do you plan to add the gemma2:2b example?
This model is very small and smart.
Best regards, Evgeny