Instructions to use UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged with Transformers:

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

pipe = pipeline("image-text-to-text", model="UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged")
model = AutoModelForImageTextToText.from_pretrained("UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged")
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

vLLM

How to use UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged",
		"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/UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged

SGLang

How to use UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged 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 "UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged" \
    --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": "UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged",
		"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 "UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged" \
        --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": "UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged",
		"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 UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged with Docker Model Runner:
```
docker model run hf.co/UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged
```

Chtholly17 commited on about 3 hours ago

Commit

82fb5eb

verified ·

1 Parent(s): 3fbd09a

Update README: add author list, real GitHub/Collection/project-page URLs

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -28,9 +28,9 @@ This release is the **Stage-3 step-186** checkpoint, which gave the largest gain
 | Resource | Link |
 |---|---|
 | 📄 Paper | <TODO_PAPER_URL> |
-| 💻 Code | https://github.com/<TODO>/VLM-CapCurriculum |
-| 🌐 Project page | <TODO_WEBSITE> |
-| 🤗 Collection (model + data + eval) | https://huggingface.co/collections/UCSC-VLAA/<TODO> |
 ## Headline numbers (extended benchmark suite, AVG over 10 benchmarks)
@@ -54,7 +54,7 @@ InternVL3 needs damped optimisation in Stage 2 to avoid entropy explosion (`lr=3
 All three stages share **one** system / format prompt — see [Inference](#inference) below.
-Detailed launch scripts: [`training/examples/internvl3_8b/`](https://github.com/<TODO>/VLM-CapCurriculum/tree/main/training/examples/internvl3_8b) in the code repo.
 ## Inference
@@ -74,7 +74,7 @@ lmdeploy serve api_server UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged \
   --server-port 23342 --tp 4
 ```
-For VLMEvalKit-style benchmark eval, plug it in via the `InternVL3_8B_Staged` alias defined in [`evaluation/configs/models.py`](https://github.com/<TODO>/VLM-CapCurriculum/blob/main/evaluation/configs/models.py).
 ## Intended use & limitations
@@ -89,7 +89,7 @@ Released under **Apache-2.0**, matching the upstream backbone. If you use this m
 ```bibtex
 @inproceedings{vlmcapcurriculum2026,
   title  = {From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models},
-  author = {TODO},
   booktitle = {Proceedings of the International Conference on Machine Learning (ICML)},
   year   = {2026}
 }

 | Resource | Link |
 |---|---|
 | 📄 Paper | <TODO_PAPER_URL> |
+| 💻 Code | https://github.com/UCSC-VLAA/VLM-CapCurriculum |
+| 🌐 Project page | https://ucsc-vlaa.github.io/VLM-CapCurriculum |
+| 🤗 Collection (model + data + eval) | https://huggingface.co/collections/UCSC-VLAA/vlm-capcurriculum-from-seeing-to-thinking-icml-2026-6a07691f944148ccb2b183b8 |
 ## Headline numbers (extended benchmark suite, AVG over 10 benchmarks)
 All three stages share **one** system / format prompt — see [Inference](#inference) below.
+Detailed launch scripts: [`training/examples/internvl3_8b/`](https://github.com/UCSC-VLAA/VLM-CapCurriculum/tree/main/training/examples/internvl3_8b) in the code repo.
 ## Inference
   --server-port 23342 --tp 4
 ```
+For VLMEvalKit-style benchmark eval, plug it in via the `InternVL3_8B_Staged` alias defined in [`evaluation/configs/models.py`](https://github.com/UCSC-VLAA/VLM-CapCurriculum/blob/main/evaluation/configs/models.py).
 ## Intended use & limitations
 ```bibtex
 @inproceedings{vlmcapcurriculum2026,
   title  = {From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models},
+  author = {Juncheng Wu and Hardy Chen and Haoqin Tu and Xianfeng Tang and Freda Shi and Hui Liu and Hanqing Lu and Cihang Xie and Yuyin Zhou},
   booktitle = {Proceedings of the International Conference on Machine Learning (ICML)},
   year   = {2026}
 }