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

Libraries

How to use AIcell/Guava-4B with Transformers:

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

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AIcell/Guava-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": "AIcell/Guava-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/AIcell/Guava-4B

SGLang

How to use AIcell/Guava-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 "AIcell/Guava-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": "AIcell/Guava-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 "AIcell/Guava-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": "AIcell/Guava-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"
						}
					}
				]
			}
		]
	}'

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

guava-v13b-qwen3.5-4b

A Qwen3.5-VL 4B model fine-tuned on the Guava SFT data robot-manipulation dataset (2,268 episodes across 16 tabletop tasks).

Training data: AIcell/Guava-4B-SFT-data.

Model


Architecture	`Qwen3_5ForConditionalGeneration` (vision + text)
Precision	bfloat16
Hidden size	2560, 32 layers (linear attention, full attention every 4th)
Vocab	248,320
Max positions	262,144
Vision	24-layer ViT, patch 16, merge 2
Shards	2 safetensors, 8.47 GiB total

Usage

from transformers import AutoModelForImageTextToText, AutoProcessor

model = AutoModelForImageTextToText.from_pretrained(
    "AIcell/Guava-4B", dtype="bfloat16", device_map="auto"
)
processor = AutoProcessor.from_pretrained("AIcell/Guava-4B")

Episodes in the training data contain up to 30 images, and coordinates are already table-aligned (tabletop is z = 0) — do not apply table-height normalization a second time.

Tasks

apple_juice_order, bread_near_lemon, can_in_bin, close_drawer, cube_stack, cube_under_cup, hotdog_near_donut, milk_near_cup, open_drawer, pick_up_orange, push_basket, push_cereal, red_objects_in_basket, remove_cube_from_tray, shell_game, tomato_in_bowl

Downloads last month: 52

Safetensors

Model size

504k params

Tensor type

BF16

Model tree for AIcell/Guava-4B

Quantizations

2 models

Collection including AIcell/Guava-4B

Guava

Collection

An effective and universal harness for embodied manipulation • 3 items • Updated 13 days ago • 1