Instructions to use javierbits/Javi0.4-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use javierbits/Javi0.4-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="javierbits/Javi0.4-2B")
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("javierbits/Javi0.4-2B")
model = AutoModelForMultimodalLM.from_pretrained("javierbits/Javi0.4-2B", 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 javierbits/Javi0.4-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "javierbits/Javi0.4-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "javierbits/Javi0.4-2B",
		"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/javierbits/Javi0.4-2B

SGLang

How to use javierbits/Javi0.4-2B 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 "javierbits/Javi0.4-2B" \
    --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": "javierbits/Javi0.4-2B",
		"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 "javierbits/Javi0.4-2B" \
        --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": "javierbits/Javi0.4-2B",
		"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 javierbits/Javi0.4-2B with Docker Model Runner:
```
docker model run hf.co/javierbits/Javi0.4-2B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Javi0.4-2B

Javi0.4-2B is Javi0.3-2B with one embedding row changed. No fine-tuning, no new data, no gradients. The tied input/output row for token 51187 (=open_page) is multiplied by 0.84. Every other weight is byte-identical to Javi0.3-2B.

The edit biases one decision: after a failed lookup, call web_search again instead of opening a URL typed from memory. It does not add a new reasoning capability.

Measured effect

8 held-out eval-v3 canonical fail questions, first web_search forced to fail, greedy next tool:

model	next `web_search`	next `open_page`
Javi0.3-2B	0/8	8/8
Javi0.4-2B	7/8	1/8

This is a targeted probe, not the full eval v3. In a two-seed harness canary with real tools and sampling, 0.84 chose open_page after a permanently blocked search and completed, same as the base; it used one extra search on a normal lookup. A 0.75 scale flipped 4/4 but looped on 14 searches under a permanent block, so 0.84 is the conservative setting.

The edit reaches the canonical open_page tool. In opencode/grok, webfetch/web_fetch after a 403 is unchanged. Full eval v3/v3f was not run.

Files

Merged bf16 safetensors (one shard, 4.2 GB), tokenizer, processor files and chat template. The vision tower is Qwen3.5-2B's, unchanged; the edit is in the language model only.

Run it

Javi was trained and evaluated with thinking off. Send "chat_template_kwargs": {"enable_thinking": false} and use temperature 0.2, top-p 0.8, top-k 20 so tool calls stay well formed.

GGUF for llama.cpp, lmdeck or lmswitch: Javi0.4-2B-GGUF.

lmdeck

lmdeck use javi0.4-2b

lmswitch

lmswitch on javi0.4-2b

Transformers

from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "javierbits/Javi0.4-2B"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(model_id, dtype="auto", device_map="auto")

tools = [{"type": "function", "function": {
    "name": "web_search", "description": "Search the web.",
    "parameters": {"type": "object", "properties": {"query": {"type": "string"}}, "required": ["query"]}}}]
messages = [{"role": "user", "content": [{"type": "text", "text": "What's the latest stable Rust release?"}]}]

inputs = processor.apply_chat_template(messages, tools=tools, add_generation_prompt=True, enable_thinking=False,
                                       tokenize=True, return_dict=True, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512, do_sample=True, temperature=0.2, top_p=0.8, top_k=20)
print(processor.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

The edit

embed_tokens[51187] *= 0.84  # =open_page

Token 51187 is a single token in the Qwen3.5 tokenizer. The row is tied between input and output embeddings, so the output logit for =open_page is reduced.