top | item 44391114

(no title)

pilooch | 8 months ago

This model is fully compatible with anything previously done with gemma3. Just passed it to one of my vlm fine-tuning scripts and it started without issues (hf transformer code). On a single GPU with Lora the E4B model takes 18Gb of VRAM in batch size 1 where gemma-4B was 21Gb. Nice one from deepmind, the gemma3 family tops the open weights VLLMs.

discuss

order

pilooch|8 months ago

Fix: it's the E2B