Test Gemma

I tested the Gemma model this morning. My computer has 32G RAM and an RTX 2070 graphics card (8G). I downloaded the 2B model. There are un-tuned and instruction-tuned versions, each of which is about 3.9G after unpacking. I executed it in CPU mode, but it crashed after a while. I guessed it may be because there is not enough memory. Then I used GPU mode to execute, the results were as follows:

Untuned 2B

Instruction-tuned 2B

The GitHub page contains a Colab basic tutorial on how to fine tune Gemma for a task, such as English to French translation. Maybe I can test it later.

---

System Requirements suggested by Google

Gemma can run on a CPU, GPU and TPU. For GPU, we recommend a 8GB+ RAM on GPU for the 2B checkpoint and 24GB+ RAM on GPU for the 7B checkpoint.