Instructions to use jvr0x/Javi0.3-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jvr0x/Javi0.3-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="jvr0x/Javi0.3-4B")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("jvr0x/Javi0.3-4B")
model = AutoModelForMultimodalLM.from_pretrained("jvr0x/Javi0.3-4B", device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jvr0x/Javi0.3-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jvr0x/Javi0.3-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jvr0x/Javi0.3-4B",
		"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/jvr0x/Javi0.3-4B

SGLang

How to use jvr0x/Javi0.3-4B 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 "jvr0x/Javi0.3-4B" \
    --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": "jvr0x/Javi0.3-4B",
		"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 "jvr0x/Javi0.3-4B" \
        --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": "jvr0x/Javi0.3-4B",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use jvr0x/Javi0.3-4B with Docker Model Runner:
```
docker model run hf.co/jvr0x/Javi0.3-4B
```

jvr0x commited on 15 days ago

Commit

c05abab

verified ·

1 Parent(s): 34fc9bb

Card: link the Javi0.3 article on X

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -32,6 +32,8 @@ What changed since [Javi0.2](https://huggingface.co/jvr0x/Javi0.2-4B-GGUF), all
 - **Honest when everything is broken.** It says what it tried, gives its best answer clearly labeled as unverified, and names where to check, without inventing a URL.
 - **No loops.** It repeats an identical call in 3% of tasks (base: 11%).
 ## Files
 The merged model in bf16 safetensors (two shards, 9.3 GB), with the base model's tokenizer, processor files and chat template. The LoRA touched the language model only; the vision tower is the base model's, unchanged, and Javi was never trained or evaluated on images.
@@ -141,7 +143,7 @@ Against the base model, Javi0.3-4B is ahead by 0.05, but the 95% interval is -0.
 **Merge:** the adapter was merged into the bf16 base with Unsloth.
-The story of every round, including each way it broke along the way, is on X: [@jvr0x](https://x.com/jvr0x).
 ## Limitations

 - **Honest when everything is broken.** It says what it tried, gives its best answer clearly labeled as unverified, and names where to check, without inventing a URL.
 - **No loops.** It repeats an identical call in 3% of tasks (base: 11%).
+How it was built, every mistake included: [the Javi0.3 article on X](https://x.com/jvr0x/status/2109266234512379964).
 ## Files
 The merged model in bf16 safetensors (two shards, 9.3 GB), with the base model's tokenizer, processor files and chat template. The LoRA touched the language model only; the vision tower is the base model's, unchanged, and Javi was never trained or evaluated on images.
 **Merge:** the adapter was merged into the bf16 base with Unsloth.
+The story of every round, including each way it broke along the way, is in [the Javi0.3 article on X](https://x.com/jvr0x/status/2109266234512379964).
 ## Limitations