Instructions to use yashpratap/gemma3n-e4b-it-generic-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yashpratap/gemma3n-e4b-it-generic-adapter with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3n-E4B-it")
model = PeftModel.from_pretrained(base_model, "yashpratap/gemma3n-e4b-it-generic-adapter")

Transformers

How to use yashpratap/gemma3n-e4b-it-generic-adapter with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="yashpratap/gemma3n-e4b-it-generic-adapter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("yashpratap/gemma3n-e4b-it-generic-adapter", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yashpratap/gemma3n-e4b-it-generic-adapter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yashpratap/gemma3n-e4b-it-generic-adapter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yashpratap/gemma3n-e4b-it-generic-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yashpratap/gemma3n-e4b-it-generic-adapter

SGLang

How to use yashpratap/gemma3n-e4b-it-generic-adapter with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "yashpratap/gemma3n-e4b-it-generic-adapter" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yashpratap/gemma3n-e4b-it-generic-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "yashpratap/gemma3n-e4b-it-generic-adapter" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yashpratap/gemma3n-e4b-it-generic-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use yashpratap/gemma3n-e4b-it-generic-adapter with Docker Model Runner:
```
docker model run hf.co/yashpratap/gemma3n-e4b-it-generic-adapter
```

gemma3n-e4b-it-generic-adapter

File size: 1,251 Bytes

a64ad70

{
    "crop_size": null,
    "data_format": "channels_first",
    "default_to_square": false,
    "device": null,
    "disable_grouping": null,
    "dither": 0.0,
    "do_center_crop": null,
    "do_convert_rgb": null,
    "do_normalize": false,
    "do_rescale": true,
    "do_resize": true,
    "feature_extractor_type": "Gemma3nAudioFeatureExtractor",
    "feature_size": 128,
    "fft_length": 1024,
    "fft_overdrive": true,
    "frame_length": 512,
    "hop_length": 160,
    "image_mean": [
      0.5,
      0.5,
      0.5
    ],
    "image_processor_type": "SiglipImageProcessorFast",
    "image_seq_length": 256,
    "image_std": [
      0.5,
      0.5,
      0.5
    ],
    "input_data_format": null,
    "input_scale_factor": 1.0,
    "max_frequency": 7600.0,
    "mel_floor": 1e-05,
    "min_frequency": 125.0,
    "padding_side": "right",
    "padding_value": 0.0,
    "per_bin_mean": null,
    "per_bin_stddev": null,
    "preemphasis": 0.97,
    "preemphasis_htk_flavor": true,
    "processor_class": "Gemma3nProcessor",
    "resample": 2,
    "rescale_factor": 0.00392156862745098,
    "return_attention_mask": true,
    "return_tensors": null,
    "sampling_rate": 16000,
    "size": {
      "height": 768,
      "width": 768
    }
}