Instructions to use tjcrims0n/g4-ann with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tjcrims0n/g4-ann with Transformers:

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

pipe = pipeline("text-generation", model="tjcrims0n/g4-ann")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("tjcrims0n/g4-ann")
model = AutoModelForMultimodalLM.from_pretrained("tjcrims0n/g4-ann")
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 Settings

vLLM

How to use tjcrims0n/g4-ann with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tjcrims0n/g4-ann"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tjcrims0n/g4-ann",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tjcrims0n/g4-ann

SGLang

How to use tjcrims0n/g4-ann 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 "tjcrims0n/g4-ann" \
    --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": "tjcrims0n/g4-ann",
		"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 "tjcrims0n/g4-ann" \
        --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": "tjcrims0n/g4-ann",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tjcrims0n/g4-ann with Docker Model Runner:
```
docker model run hf.co/tjcrims0n/g4-ann
```

g4-ann

Full Transformers safetensors model based on google/gemma-4-E4B-it.

Notes

This is a Gemma-family model.
annihilate_merge_metadata.json records the base model used for this export.
The repo includes the chat template, tokenizer, generation config, processor config, and full model weights.

Quick Load

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "tjcrims0n/g4-ann"
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, device_map="auto")

messages = [{"role": "user", "content": "Hello."}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
outputs = model.generate(inputs, max_new_tokens=80)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Smoke Test Notes

A local smoke test returned coherent answers for greeting, arithmetic, and model-family identity prompts.

Downloads last month: 22

Safetensors

Model size

8B params

Tensor type

F16

Model tree for tjcrims0n/g4-ann

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Finetuned

(231)

this model