Instructions to use review-artifacts/nsdl-7b-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use review-artifacts/nsdl-7b-sft with Transformers:

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

pipe = pipeline("image-text-to-text", model="review-artifacts/nsdl-7b-sft")
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("review-artifacts/nsdl-7b-sft")
model = AutoModelForMultimodalLM.from_pretrained("review-artifacts/nsdl-7b-sft", 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 review-artifacts/nsdl-7b-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "review-artifacts/nsdl-7b-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "review-artifacts/nsdl-7b-sft",
		"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/review-artifacts/nsdl-7b-sft

SGLang

How to use review-artifacts/nsdl-7b-sft 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 "review-artifacts/nsdl-7b-sft" \
    --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": "review-artifacts/nsdl-7b-sft",
		"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 "review-artifacts/nsdl-7b-sft" \
        --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": "review-artifacts/nsdl-7b-sft",
		"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 review-artifacts/nsdl-7b-sft with Docker Model Runner:
```
docker model run hf.co/review-artifacts/nsdl-7b-sft
```

NSDL 7B (SFT), VIKI-L2 main row: anonymized checkpoint for double-anonymous review

Row "Table 1: NSDL 7B (SFT); Table 3 ablations; VIKI-trained transfer row of Table 2" of the submission. Weights are stored in bfloat16, the dtype the evaluation loader uses. Load and run with the code in the anonymized repository linked from the paper (nsdl/ + scripts/eval_lnsdl_agentic_viki_l2.py); evaluation flags are in that repository's README.

Provided for peer review only; do not redistribute during review. Author, affiliation and citation information is intentionally omitted.

File	Bytes	sha256
`added_tokens.json`	605	`58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b`
`chat_template.json`	1049	`94174d7176c52a7192f96fc34eb2cf23c7c2059d63cdbfadca1586ba89731fb7`
`config.json`	1541	`ccba9eb5596f73369f80d46f87b9725053c0e9abe4f09ccbef3b945be9a5a71e`
`generation_config.json`	260	`90e92cbc8634d6f5b1cb1ae58a3c48724a1ce1f11f8b7aecb5b9b3fd5d5a06bf`
`merges.txt`	1671853	`8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5`
`model-00001-of-00004.safetensors`	5298562264	`5907eb1e676772128894ee2f8a32b779e4ad9a3e2f752b02827305227857c3cd`
`model-00002-of-00004.safetensors`	5340152256	`9448ae2f0c28e539d0dcccb0e5ea270b90d340f6a6d316372b172de2ac2eacdf`
`model-00003-of-00004.safetensors`	5343777832	`658e84daa595214810429a8114b9d8f59064fa13540dc083838addb9de2a3fc8`
`model-00004-of-00004.safetensors`	601922224	`d96061794d06498c6a87aa2576e8f286cbe3f1e0901bc8d3a2917b38174147e9`
`model.safetensors.index.json`	57618	`e8e945d6900a45f894339603764940658a2999f842354256c3ef06b638ee4249`
`preprocessor_config.json`	575	`549c158011407dfb750d9ec578047cf76f5bfe365cd0aa069a50137d3f98d9dd`
`special_tokens_map.json`	613	`76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd`
`tokenizer.json`	11421995	`33624f49f1034c4f5d92e3ec47ccdf80ccd02caf1eb1d769872ba7fb1e5be112`
`tokenizer_config.json`	5776	`0a6be425d5d62ec1904deb45e569c809d0973bd39a411452388f268a855e3183`
`vocab.json`	2776833	`ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910`

Downloads last month: 12

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for review-artifacts/nsdl-7b-sft

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Finetuned

(1239)

this model