Instructions to use josephmayo/gemma-4-E4B-it-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use josephmayo/gemma-4-E4B-it-Coder with Transformers:

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

pipe = pipeline("image-text-to-text", model="josephmayo/gemma-4-E4B-it-Coder")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("josephmayo/gemma-4-E4B-it-Coder")
model = AutoModelForImageTextToText.from_pretrained("josephmayo/gemma-4-E4B-it-Coder")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use josephmayo/gemma-4-E4B-it-Coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "josephmayo/gemma-4-E4B-it-Coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "josephmayo/gemma-4-E4B-it-Coder",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/josephmayo/gemma-4-E4B-it-Coder

SGLang

How to use josephmayo/gemma-4-E4B-it-Coder 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 "josephmayo/gemma-4-E4B-it-Coder" \
    --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": "josephmayo/gemma-4-E4B-it-Coder",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "josephmayo/gemma-4-E4B-it-Coder" \
        --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": "josephmayo/gemma-4-E4B-it-Coder",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use josephmayo/gemma-4-E4B-it-Coder with Docker Model Runner:
```
docker model run hf.co/josephmayo/gemma-4-E4B-it-Coder
```

gemma-4-E4B-it-Coder / trainer_log_history.json

josephmayo

Upload proof trainer_log_history.json

23b2c11 verified 14 days ago

raw

history blame contribute delete

6.62 kB

	[
	{
	"loss": 2.7602264404296877,
	"grad_norm": 3.374150276184082,
	"learning_rate": 6.666666666666667e-05,
	"epoch": 0.078125,
	"step": 5
	},
	{
	"loss": 1.8698038101196288,
	"grad_norm": 1.457783579826355,
	"learning_rate": 9.994100796397954e-05,
	"epoch": 0.15625,
	"step": 10
	},
	{
	"loss": 1.319937038421631,
	"grad_norm": 0.707484245300293,
	"learning_rate": 9.958100506132127e-05,
	"epoch": 0.234375,
	"step": 15
	},
	{
	"loss": 1.3707428932189942,
	"grad_norm": 0.43754199147224426,
	"learning_rate": 9.889612861977853e-05,
	"epoch": 0.3125,
	"step": 20
	},
	{
	"loss": 1.3082144737243653,
	"grad_norm": 0.35036444664001465,
	"learning_rate": 9.789086620939936e-05,
	"epoch": 0.390625,
	"step": 25
	},
	{
	"loss": 1.283499526977539,
	"grad_norm": 0.26873722672462463,
	"learning_rate": 9.657180469054213e-05,
	"epoch": 0.46875,
	"step": 30
	},
	{
	"loss": 1.1428126335144042,
	"grad_norm": 0.31287550926208496,
	"learning_rate": 9.494758705426978e-05,
	"epoch": 0.546875,
	"step": 35
	},
	{
	"loss": 1.1817453384399415,
	"grad_norm": 0.2988075911998749,
	"learning_rate": 9.302885579019627e-05,
	"epoch": 0.625,
	"step": 40
	},
	{
	"loss": 1.1872751235961914,
	"grad_norm": 0.2937701642513275,
	"learning_rate": 9.082818315286055e-05,
	"epoch": 0.703125,
	"step": 45
	},
	{
	"loss": 1.146270751953125,
	"grad_norm": 0.3410361111164093,
	"learning_rate": 8.835998878354931e-05,
	"epoch": 0.78125,
	"step": 50
	},
	{
	"loss": 1.167984962463379,
	"grad_norm": 0.3269799053668976,
	"learning_rate": 8.564044522734147e-05,
	"epoch": 0.859375,
	"step": 55
	},
	{
	"loss": 1.0844226837158204,
	"grad_norm": 0.44009652733802795,
	"learning_rate": 8.268737196446264e-05,
	"epoch": 0.9375,
	"step": 60
	},
	{
	"loss": 1.1493185043334961,
	"grad_norm": 0.383281409740448,
	"learning_rate": 7.952011865029614e-05,
	"epoch": 1.015625,
	"step": 65
	},
	{
	"loss": 1.1071245193481445,
	"grad_norm": 0.40226107835769653,
	"learning_rate": 7.61594383291065e-05,
	"epoch": 1.09375,
	"step": 70
	},
	{
	"loss": 1.062960433959961,
	"grad_norm": 0.3419550359249115,
	"learning_rate": 7.262735145222696e-05,
	"epoch": 1.171875,
	"step": 75
	},
	{
	"loss": 1.1302300453186036,
	"grad_norm": 0.39782464504241943,
	"learning_rate": 6.894700159171534e-05,
	"epoch": 1.25,
	"step": 80
	},
	{
	"loss": 1.0111728668212892,
	"grad_norm": 0.3370531499385834,
	"learning_rate": 6.514250379489753e-05,
	"epoch": 1.328125,
	"step": 85
	},
	{
	"loss": 1.0343121528625487,
	"grad_norm": 0.35490792989730835,
	"learning_rate": 6.123878657343648e-05,
	"epoch": 1.40625,
	"step": 90
	},
	{
	"loss": 1.161344337463379,
	"grad_norm": 0.4397459328174591,
	"learning_rate": 5.726142856227452e-05,
	"epoch": 1.484375,
	"step": 95
	},
	{
	"loss": 1.1250411987304687,
	"grad_norm": 0.375924289226532,
	"learning_rate": 5.3236490918721794e-05,
	"epoch": 1.5625,
	"step": 100
	},
	{
	"loss": 1.0718464851379395,
	"grad_norm": 0.41714778542518616,
	"learning_rate": 4.919034655987493e-05,
	"epoch": 1.640625,
	"step": 105
	},
	{
	"loss": 1.0154043197631837,
	"grad_norm": 0.37521687150001526,
	"learning_rate": 4.51495073572676e-05,
	"epoch": 1.71875,
	"step": 110
	},
	{
	"loss": 0.9917967796325684,
	"grad_norm": 0.42887604236602783,
	"learning_rate": 4.114045042103887e-05,
	"epoch": 1.796875,
	"step": 115
	},
	{
	"loss": 1.1146905899047852,
	"grad_norm": 0.4208148717880249,
	"learning_rate": 3.718944461187138e-05,
	"epoch": 1.875,
	"step": 120
	},
	{
	"loss": 0.9283761978149414,
	"grad_norm": 0.3849687874317169,
	"learning_rate": 3.332237841745898e-05,
	"epoch": 1.953125,
	"step": 125
	},
	{
	"loss": 1.113053035736084,
	"grad_norm": 0.4142734110355377,
	"learning_rate": 2.9564590321322207e-05,
	"epoch": 2.03125,
	"step": 130
	},
	{
	"loss": 0.9842248916625976,
	"grad_norm": 0.44529953598976135,
	"learning_rate": 2.5940702775459747e-05,
	"epoch": 2.109375,
	"step": 135
	},
	{
	"loss": 0.9449721336364746,
	"grad_norm": 0.3756776750087738,
	"learning_rate": 2.2474460864709824e-05,
	"epoch": 2.1875,
	"step": 140
	},
	{
	"loss": 1.0590093612670899,
	"grad_norm": 0.4192875325679779,
	"learning_rate": 1.9188576719953633e-05,
	"epoch": 2.265625,
	"step": 145
	},
	{
	"loss": 0.9768091201782226,
	"grad_norm": 0.5095818638801575,
	"learning_rate": 1.6104580699624837e-05,
	"epoch": 2.34375,
	"step": 150
	},
	{
	"loss": 1.038302516937256,
	"grad_norm": 0.41709497570991516,
	"learning_rate": 1.3242680314639993e-05,
	"epoch": 2.421875,
	"step": 155
	},
	{
	"loss": 0.9975608825683594,
	"grad_norm": 0.5563586354255676,
	"learning_rate": 1.0621627821127289e-05,
	"epoch": 2.5,
	"step": 160
	},
	{
	"loss": 0.9714397430419922,
	"grad_norm": 0.8915637135505676,
	"learning_rate": 8.25859734853645e-06,
	"epoch": 2.578125,
	"step": 165
	},
	{
	"loss": 0.9948483467102051,
	"grad_norm": 0.4391196370124817,
	"learning_rate": 6.16907236823262e-06,
	"epoch": 2.65625,
	"step": 170
	},
	{
	"loss": 0.9389057159423828,
	"grad_norm": 0.4650712311267853,
	"learning_rate": 4.366744239922998e-06,
	"epoch": 2.734375,
	"step": 175
	},
	{
	"loss": 1.06390380859375,
	"grad_norm": 0.4836062788963318,
	"learning_rate": 2.8634225006782865e-06,
	"epoch": 2.8125,
	"step": 180
	},
	{
	"loss": 1.008359718322754,
	"grad_norm": 0.45215511322021484,
	"learning_rate": 1.6689574843694433e-06,
	"epoch": 2.890625,
	"step": 185
	},
	{
	"loss": 1.0110493659973145,
	"grad_norm": 0.5408219695091248,
	"learning_rate": 7.911757785462881e-07,
	"epoch": 2.96875,
	"step": 190
	},
	{
	"loss": 0.911649227142334,
	"grad_norm": 0.4599083364009857,
	"learning_rate": 2.3582894166930268e-07,
	"epoch": 3.046875,
	"step": 195
	},
	{
	"loss": 0.9673548698425293,
	"grad_norm": 0.43304941058158875,
	"learning_rate": 6.5558167183898955e-09,
	"epoch": 3.125,
	"step": 200
	},
	{
	"train_runtime": 4256.6409,
	"train_samples_per_second": 0.752,
	"train_steps_per_second": 0.047,
	"total_flos": 4.259313762009523e+16,
	"train_loss": 1.142699921131134,
	"epoch": 3.125,
	"step": 200
	}
	]