Unknown Model (mobilenetv5_300m_enc) when loading Gemma 3n #39208
Description
System Info
- `transformers` version: 4.53.0
- Platform: Linux-6.1.141+-x86_64-with-glibc2.35
- Python version: 3.10.12
- Huggingface_hub version: 0.33.2
- Safetensors version: 0.5.1
- Accelerate version: 1.2.1
- Accelerate config: not found
- DeepSpeed version: not installed
- PyTorch version (accelerator?): 2.5.1+cu121 (NA)
- Tensorflow version (GPU?): 2.17.1 (False)
- Flax version (CPU?/GPU?/TPU?): 0.10.2 (cpu)
- Jax version: 0.4.33
- JaxLib version: 0.4.33
- Using distributed or parallel set-up in script?: <fill in>Does Gemma 3n require special setups? That is not sustainable.
Who can help?
I upgraded to the latest transformers to try Gemma 3n and it would seem there is not implementation of mobilenetv5_300m when i try to run the model as described on the official huggingface page.
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
[<ipython-input-2-ac178faa1642>](https://localhost:8080/#) in <cell line: 8>()
6 model_id = "google/gemma-3n-e4b-it"
7
----> 8 model = Gemma3nForConditionalGeneration.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16,).eval()
9
10 processor = AutoProcessor.from_pretrained(model_id)
8 frames
[/usr/local/lib/python3.10/dist-packages/timm/models/_factory.py](https://localhost:8080/#) in create_model(model_name, pretrained, pretrained_cfg, pretrained_cfg_overlay, checkpoint_path, scriptable, exportable, no_jit, **kwargs)
111
112 if not is_model(model_name):
--> 113 raise RuntimeError('Unknown model (%s)' % model_name)
114
115 create_fn = model_entrypoint(model_name)
RuntimeError: Unknown model (mobilenetv5_300m_enc)Does Gemma 3n require special setups? That is not sustainable.
Information
- The official example scripts
- My own modified scripts
Tasks
- An officially supported task in the
examplesfolder (such as GLUE/SQuAD, ...) - My own task or dataset (give details below)
Reproduction
The example code on the model card
from transformers import AutoProcessor, Gemma3nForConditionalGeneration
from PIL import Image
import requests
import torch
model_id = "google/gemma-3n-e4b-it"
model = Gemma3nForConditionalGeneration.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16,).eval()
processor = AutoProcessor.from_pretrained(model_id)
messages = [
{
"role": "system",
"content": [{"type": "text", "text": "You are a helpful assistant."}]
},
{
"role": "user",
"content": [
{"type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image in detail."}
]
}
]
inputs = processor.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt",
).to(model.device)
input_len = inputs["input_ids"].shape[-1]
with torch.inference_mode():
generation = model.generate(**inputs, max_new_tokens=100, do_sample=False)
generation = generation[0][input_len:]
decoded = processor.decode(generation, skip_special_tokens=True)
print(decoded)Expected behavior
This is the basic example on the model card.