Instructions to use spatial-training/llava-video-72b-sims-3q-25k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spatial-training/llava-video-72b-sims-3q-25k with Transformers:

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

pipe = pipeline("image-text-to-text", model="spatial-training/llava-video-72b-sims-3q-25k")
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 AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("spatial-training/llava-video-72b-sims-3q-25k")
model = AutoModelForCausalLM.from_pretrained("spatial-training/llava-video-72b-sims-3q-25k", 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 = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use spatial-training/llava-video-72b-sims-3q-25k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "spatial-training/llava-video-72b-sims-3q-25k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "spatial-training/llava-video-72b-sims-3q-25k",
		"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/spatial-training/llava-video-72b-sims-3q-25k

SGLang

How to use spatial-training/llava-video-72b-sims-3q-25k 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 "spatial-training/llava-video-72b-sims-3q-25k" \
    --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": "spatial-training/llava-video-72b-sims-3q-25k",
		"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 "spatial-training/llava-video-72b-sims-3q-25k" \
        --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": "spatial-training/llava-video-72b-sims-3q-25k",
		"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 spatial-training/llava-video-72b-sims-3q-25k with Docker Model Runner:
```
docker model run hf.co/spatial-training/llava-video-72b-sims-3q-25k
```

LLaVA-Video-72B SIMS-V 3Q-25K

This is a full-parameter fine-tune of lmms-lab/LLaVA-Video-72B-Qwen2 on the 25K-example SIMS-V 3Q spatial-reasoning mixture.

Lineage

Base model: lmms-lab/LLaVA-Video-72B-Qwen2
Base revision: 226cce801d38f1ace080cbbf335a573500a9ce6f
Dataset: ellisbrown/SIMS-VSI
Project: SIMS-V
Training date: 2026-01-28
W&B run: ellisbrown/video_sim2real/79sc2cmj

The training mixture contains 25,000 programmatically generated examples:

Task	Examples
Absolute distance, open-ended	8,616
Appearance order, multiple-choice	6,384
Relative direction, medium	3,905
Relative direction, hard	3,853
Relative direction, easy	2,242

Training recipe

Full-parameter tuning of mm_vision_tower, mm_mlp_adapter, and mm_language_model (not LoRA)
1 epoch / 781 optimizer steps
Global batch size 32 on 16 H200 GPUs
Peak learning rate 2e-6, cosine schedule, warmup ratio 0.03
BF16, DeepSpeed ZeRO-3, gradient checkpointing
32 video frames, maximum sequence length 32,768
Final training loss: 0.12651

Evaluation

All evaluations used 32 frames. Scores below are the archived January 2026 results from the same evaluation stack for the base and fine-tuned models.

Benchmark	Base LV-72B	SIMS-V 3Q-25K
VSI-Bench	41.18	45.03
VSI-Bench (debiased)	36.78	39.99
MME-RealWorld Lite	35.96	43.41
VideoMME	68.78	69.04
EgoSchema	66.67	63.25
OpenEQA	43.81	42.51

Usage and limitations

Load this checkpoint with the LLaVA-NeXT llava_qwen video-model code path and the qwen_1_5 conversation template. This is a research checkpoint, not a general-purpose production model. It was tuned on synthetic spatial QA and can regress on unrelated video-understanding benchmarks, as the table above shows.

The base model and this derivative use the Apache 2.0 license. Users are also responsible for the terms of the Qwen2, SigLIP, LLaVA, and SIMS-V components.

Downloads last month: 13

Safetensors

Model size

73B params

Tensor type

BF16

Model tree for spatial-training/llava-video-72b-sims-3q-25k

Base model

lmms-lab/llava-onevision-qwen2-72b-si

Finetuned

lmms-lab/LLaVA-Video-72B-Qwen2