google

/

gemma-3n-E4B

like 57

Follow

Google 19.4k

Generated with

from transformers import AutoModelForCausalLM
import torch 

repo_id = "gg-hf-gm/gemma-3n-E4B"
model = AutoModelForCausalLM.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map="auto")

print(f"Total Parameters: {model.num_parameters():,}") # 7,849,435,920