Instructions to use InternRobotics/VLAC-Cut with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InternRobotics/VLAC-Cut with Transformers:

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

pipe = pipeline("image-text-to-text", model="InternRobotics/VLAC-Cut")
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("InternRobotics/VLAC-Cut")
model = AutoModelForMultimodalLM.from_pretrained("InternRobotics/VLAC-Cut", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use InternRobotics/VLAC-Cut with vLLM:

Install from pip and serve model

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

SGLang

How to use InternRobotics/VLAC-Cut 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 "InternRobotics/VLAC-Cut" \
    --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": "InternRobotics/VLAC-Cut",
		"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 "InternRobotics/VLAC-Cut" \
        --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": "InternRobotics/VLAC-Cut",
		"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 InternRobotics/VLAC-Cut with Docker Model Runner:
```
docker model run hf.co/InternRobotics/VLAC-Cut
```

futurefantasy commited on about 1 month ago

Commit

4d790be

verified ·

1 Parent(s): d442ee8

Update model card and quick start docs

Browse files

Files changed (1) hide show

README.md +25 -34

README.md CHANGED Viewed

@@ -9,38 +9,31 @@ tags:
   - progress-estimation
 ---
-# VLAC2 Qwen3-VL 30B A3B Progress
-This repository contains the inference-ready VLAC2 model weights staged from the current formal checkpoint `checkpoint-2315_ver5_vlac311_formal_v2-20260512-111948`.
-## What Is Included
-- Full finetuned model weights in `safetensors` shard format
-- Tokenizer files
-- Image and video processor configs
-- Chat template used by the exported checkpoint
-- `examples/` with `3` bundled demo videos
-- `quick_start/` with one minimal inference script
-## What Is Excluded
-- DeepSpeed optimizer states
-- `global_step*` recovery directories
-- RNG snapshots
-- Trainer logs and internal resume artifacts
-## Base Model
-- Base checkpoint: `Qwen/Qwen3-VL-30B-A3B-Instruct`
-- Exported architecture: `Qwen3VLMoeForConditionalGeneration`
-- Recommended VLAC model type in local evaluation scripts: `qwen3_moe_vl`
-## Suggested Loading
 ```python
 from transformers import AutoModelForImageTextToText, AutoProcessor
-model_id = "YOUR_ORG/VLAC2-Qwen3VL-30B-A3B-Progress"
 processor = AutoProcessor.from_pretrained(model_id)
 model = AutoModelForImageTextToText.from_pretrained(
@@ -50,23 +43,21 @@ model = AutoModelForImageTextToText.from_pretrained(
 )
 ```
-## Local VLAC Evaluation
-Use this staged model repo with the existing benchmark scripts by passing:
 ```bash
-MODEL_PATH=/path/to/VLAC2-Qwen3VL-30B-A3B-Progress
-MODEL_TYPE=qwen3_moe_vl
 ```
-## Bundled Demo
-- examples: `examples/`
-- quick start: `quick_start/README.md`
-- simple runner: `quick_start/run_example.py`
-## Notes Before Public Release
-- Fill in the final license.
-- Add the final citation and dataset repo link.
-- If you publish the benchmark separately, link it here via the model card metadata.

   - progress-estimation
 ---
+# VLAC2-Qwen3VL-30B-A3B-Progress
+VLAC2-Qwen3VL-30B-A3B-Progress is a video-language progress estimation model for robotic manipulation. Given a task description and a video, it predicts time-progress keypoints that can be aligned into a dense progress curve.
+This release contains the inference-ready model weights, tokenizer and processor files, three bundled demo episodes, and a minimal local inference example.
+## Model
+- Base model: `Qwen/Qwen3-VL-30B-A3B-Instruct`
+- Architecture: `Qwen3VLMoeForConditionalGeneration`
+- Recommended VLAC model type in local evaluation scripts: `qwen3_moe_vl`
+- Bundled quick start uses the `chunk_all` prompt and samples the input video at `2 Hz`
+## Highlights
+- Progress estimation for long-horizon manipulation videos
+- Rollback and regression recognition in non-expert trajectories
+- Bundled demos for both expert and non-expert episodes
+## Use with Transformers
 ```python
 from transformers import AutoModelForImageTextToText, AutoProcessor
+model_id = "InternRobotics/VLAC2-Qwen3VL-30B-A3B-Progress"
 processor = AutoProcessor.from_pretrained(model_id)
 model = AutoModelForImageTextToText.from_pretrained(
 )
 ```
+## Quick Start
+Run one of the bundled examples from the model release root:
 ```bash
+python quick_start/run_example.py --example-id example_01
+python quick_start/run_example.py --example-id example_02
+python quick_start/run_example.py --example-id example_03
 ```
+For local VLAC benchmark scripts, use:
+```bash
+MODEL_PATH=/path/to/VLAC2-Qwen3VL-30B-A3B-Progress
+MODEL_TYPE=qwen3_moe_vl
+```
+More details are provided in `quick_start/README.md`.