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 / summary.json

josephmayo

Upload proof summary.json

cab4529 verified 14 days ago

raw

history blame contribute delete

4.52 kB

	{
	"run_id": "20260512_190433",
	"model_id": "google/gemma-4-E4B-it",
	"dataset_id": "ise-uiuc/Magicoder-Evol-Instruct-110K",
	"adapter_repo": "josephmayo/gemma-4-E4B-it-coding-lora",
	"merged_repo": "josephmayo/gemma-4-E4B-it-coding-merged",
	"stage": "after_eval",
	"errors": [],
	"cuda_available": true,
	"cuda_device_count": 2,
	"devices": [
	"Tesla T4",
	"Tesla T4"
	],
	"torch_version_initial": "2.10.0+cu128",
	"hf_token_present": false,
	"max_train_samples": 1024,
	"max_steps": 200,
	"max_seq_length": 512,
	"eval_count": 8,
	"lora_r": 16,
	"lora_alpha": 32,
	"lr": 0.0001,
	"grad_accum": 8,
	"push_to_hf": true,
	"merge_and_push": false,
	"load_in_4bit": true,
	"memory_after_load": [
	0,
	9302143488
	],
	"eval_source": "openai/openai_humaneval:8",
	"baseline_avg_score": 0.76875,
	"safe_train_rows": 1024,
	"trainable_parameters": {
	"trainable": 50499584,
	"total": 7991600416
	},
	"log_history_tail": [
	{
	"loss": 1.0154043197631837,
	"grad_norm": 0.37521687150001526,
	"learning_rate": 4.51495073572676e-05,
	"epoch": 1.71875
	},
	{
	"loss": 0.9917967796325684,
	"grad_norm": 0.42887604236602783,
	"learning_rate": 4.114045042103887e-05,
	"epoch": 1.796875
	},
	{
	"loss": 1.1146905899047852,
	"grad_norm": 0.4208148717880249,
	"learning_rate": 3.718944461187138e-05,
	"epoch": 1.875
	},
	{
	"loss": 0.9283761978149414,
	"grad_norm": 0.3849687874317169,
	"learning_rate": 3.332237841745898e-05,
	"epoch": 1.953125
	},
	{
	"loss": 1.113053035736084,
	"grad_norm": 0.4142734110355377,
	"learning_rate": 2.9564590321322207e-05,
	"epoch": 2.03125
	},
	{
	"loss": 0.9842248916625976,
	"grad_norm": 0.44529953598976135,
	"learning_rate": 2.5940702775459747e-05,
	"epoch": 2.109375
	},
	{
	"loss": 0.9449721336364746,
	"grad_norm": 0.3756776750087738,
	"learning_rate": 2.2474460864709824e-05,
	"epoch": 2.1875
	},
	{
	"loss": 1.0590093612670899,
	"grad_norm": 0.4192875325679779,
	"learning_rate": 1.9188576719953633e-05,
	"epoch": 2.265625
	},
	{
	"loss": 0.9768091201782226,
	"grad_norm": 0.5095818638801575,
	"learning_rate": 1.6104580699624837e-05,
	"epoch": 2.34375
	},
	{
	"loss": 1.038302516937256,
	"grad_norm": 0.41709497570991516,
	"learning_rate": 1.3242680314639993e-05,
	"epoch": 2.421875
	},
	{
	"loss": 0.9975608825683594,
	"grad_norm": 0.5563586354255676,
	"learning_rate": 1.0621627821127289e-05,
	"epoch": 2.5
	},
	{
	"loss": 0.9714397430419922,
	"grad_norm": 0.8915637135505676,
	"learning_rate": 8.25859734853645e-06,
	"epoch": 2.578125
	},
	{
	"loss": 0.9948483467102051,
	"grad_norm": 0.4391196370124817,
	"learning_rate": 6.16907236823262e-06,
	"epoch": 2.65625
	},
	{
	"loss": 0.9389057159423828,
	"grad_norm": 0.4650712311267853,
	"learning_rate": 4.366744239922998e-06,
	"epoch": 2.734375
	},
	{
	"loss": 1.06390380859375,
	"grad_norm": 0.4836062788963318,
	"learning_rate": 2.8634225006782865e-06,
	"epoch": 2.8125
	},
	{
	"loss": 1.008359718322754,
	"grad_norm": 0.45215511322021484,
	"learning_rate": 1.6689574843694433e-06,
	"epoch": 2.890625
	},
	{
	"loss": 1.0110493659973145,
	"grad_norm": 0.5408219695091248,
	"learning_rate": 7.911757785462881e-07,
	"epoch": 2.96875
	},
	{
	"loss": 0.911649227142334,
	"grad_norm": 0.4599083364009857,
	"learning_rate": 2.3582894166930268e-07,
	"epoch": 3.046875
	},
	{
	"loss": 0.9673548698425293,
	"grad_norm": 0.43304941058158875,
	"learning_rate": 6.5558167183898955e-09,
	"epoch": 3.125
	},
	{
	"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
	}
	],
	"train_metrics": {
	"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
	},
	"after_avg_score": 0.76875,
	"score_delta": 0.0,
	"adapter_dir": "/kaggle/working/gemma4_e4b_coding_lora",
	"release_gate_pass": true
	}