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

4bde30c

verified ·

1 Parent(s): c52a7a7

Rename repo to VLAC-Cut and fix parameter metadata

Browse files

Files changed (4) hide show

README.md +4 -4
model.safetensors.index.json +1 -1
quick_start/README.md +1 -1
training_summary.json +2 -2

README.md CHANGED Viewed

@@ -9,9 +9,9 @@ tags:
   - progress-estimation
 ---
-# VLAC-Cut-Qwen3VL-30B-A3B-Progress
-VLAC-Cut-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 progress curve.
 This release contains the inference-ready model weights, tokenizer and processor files, three bundled demo episodes, reference prediction outputs, and minimal local inference utilities.
@@ -33,7 +33,7 @@ This release contains the inference-ready model weights, tokenizer and processor
 ```python
 from transformers import AutoModelForImageTextToText, AutoProcessor
-model_id = "InternRobotics/VLAC-Cut-Qwen3VL-30B-A3B-Progress"
 processor = AutoProcessor.from_pretrained(model_id)
 model = AutoModelForImageTextToText.from_pretrained(
@@ -49,7 +49,7 @@ Run progress inference on an arbitrary video:
 ```bash
 python quick_start/run_example.py \
-  --model-path /path/to/VLAC-Cut-Qwen3VL-30B-A3B-Progress \
   --video-path /path/to/video.mp4 \
   --task-instruction "<natural-language task instruction>" \
   --task-plan $'<optional step-by-step task plan>' \

   - progress-estimation
 ---
+# VLAC-Cut
+VLAC-Cut 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 progress curve.
 This release contains the inference-ready model weights, tokenizer and processor files, three bundled demo episodes, reference prediction outputs, and minimal local inference utilities.
 ```python
 from transformers import AutoModelForImageTextToText, AutoProcessor
+model_id = "InternRobotics/VLAC-Cut"
 processor = AutoProcessor.from_pretrained(model_id)
 model = AutoModelForImageTextToText.from_pretrained(
 ```bash
 python quick_start/run_example.py \
+  --model-path /path/to/VLAC-Cut \
   --video-path /path/to/video.mp4 \
   --task-instruction "<natural-language task instruction>" \
   --task-plan $'<optional step-by-step task plan>' \

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_parameters": 664816,
     "total_size": 62141508064
   },
   "weight_map": {

 {
   "metadata": {
+    "total_parameters": 31070754032,
     "total_size": 62141508064
   },
   "weight_map": {

quick_start/README.md CHANGED Viewed

@@ -23,7 +23,7 @@ Run inference:
 ```bash
 python quick_start/run_example.py \
-  --model-path /path/to/VLAC-Cut-Qwen3VL-30B-A3B-Progress \
   --video-path /path/to/video.mp4 \
   --task-instruction "<natural-language task instruction>" \
   --task-plan $'<optional step-by-step task plan>' \

 ```bash
 python quick_start/run_example.py \
+  --model-path /path/to/VLAC-Cut \
   --video-path /path/to/video.mp4 \
   --task-instruction "<natural-language task instruction>" \
   --task-plan $'<optional step-by-step task plan>' \

training_summary.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "model_name": "VLAC2-Qwen3VL-30B-A3B-Progress",
   "base_model": "Qwen/Qwen3-VL-30B-A3B-Instruct",
   "exported_architecture": "Qwen3VLMoeForConditionalGeneration",
   "config_model_type": "qwen3_vl_moe",
@@ -8,7 +8,7 @@
   "template": "qwen3_vl",
   "transformers_version": "4.57.6",
   "notes": [
-    "Released VLAC2 model for video-language progress estimation in robotic manipulation.",
     "This summary records the base model and runtime loading information for the released checkpoint."
   ]
 }

 {
+  "model_name": "VLAC-Cut",
   "base_model": "Qwen/Qwen3-VL-30B-A3B-Instruct",
   "exported_architecture": "Qwen3VLMoeForConditionalGeneration",
   "config_model_type": "qwen3_vl_moe",
   "template": "qwen3_vl",
   "transformers_version": "4.57.6",
   "notes": [
+    "Released VLAC-Cut model for video-language progress estimation in robotic manipulation.",
     "This summary records the base model and runtime loading information for the released checkpoint."
   ]
 }