Instructions to use LiquidAI/d1-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/d1-3B with Transformers:

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

pipe = pipeline("image-text-to-text", model="LiquidAI/d1-3B", trust_remote_code=True)
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("LiquidAI/d1-3B", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("LiquidAI/d1-3B", trust_remote_code=True, 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LiquidAI/d1-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/d1-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LiquidAI/d1-3B",
		"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/LiquidAI/d1-3B

SGLang

How to use LiquidAI/d1-3B 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 "LiquidAI/d1-3B" \
    --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": "LiquidAI/d1-3B",
		"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 "LiquidAI/d1-3B" \
        --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": "LiquidAI/d1-3B",
		"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 LiquidAI/d1-3B with Docker Model Runner:
```
docker model run hf.co/LiquidAI/d1-3B
```

ybelkada HF Staff commited on 1 day ago

Commit

2f0e3e3

verified ·

1 Parent(s): 051bcc4

Add safeagents judge bench results

Browse files

Hi! This adds `LiquidAI/d1-3B`'s results on the [safeagents judge bench](https://huggingface.co/datasets/harness-hub/safeagents-judge-bench), a benchmark of real agent tool calls that [safeagents](https://github.com/huggingface/safeagents)' scanner flags as suspicious, each labelled block or allow and with a kind of misuse (reward hacking, harness introspection, credential misuse, ...).

On the 562 test calls: balanced accuracy 0.823, AUROC 0.919, false-block rate 0.026, category macro F1 0.238. Run zero-shot, one System One request per call, on Apple M5 Pro (MPS). Per-call verdicts are in the dataset's `results/` folder.

The file is named after the benchmark, so it doesn't touch any existing `.eval_results` file.

Files changed (1) hide show

.eval_results/safeagents-judge-bench.yaml +32 -0

.eval_results/safeagents-judge-bench.yaml ADDED Viewed

	@@ -0,0 +1,32 @@

+- dataset:
+    id: harness-hub/safeagents-judge-bench
+    task_id: balanced_accuracy
+  value: 0.823
+  date: "2026-10-30"
+  source:
+    url: https://huggingface.co/datasets/harness-hub/safeagents-judge-bench
+    name: "safeagents judge bench v0, test split, run on Apple M5 Pro (MPS)"
+- dataset:
+    id: harness-hub/safeagents-judge-bench
+    task_id: auroc
+  value: 0.919
+  date: "2026-10-30"
+  source:
+    url: https://huggingface.co/datasets/harness-hub/safeagents-judge-bench
+    name: "safeagents judge bench v0, test split, run on Apple M5 Pro (MPS)"
+- dataset:
+    id: harness-hub/safeagents-judge-bench
+    task_id: false_block_rate
+  value: 0.026
+  date: "2026-10-30"
+  source:
+    url: https://huggingface.co/datasets/harness-hub/safeagents-judge-bench
+    name: "safeagents judge bench v0, test split, run on Apple M5 Pro (MPS)"
+- dataset:
+    id: harness-hub/safeagents-judge-bench
+    task_id: category_macro_f1
+  value: 0.238
+  date: "2026-10-30"
+  source:
+    url: https://huggingface.co/datasets/harness-hub/safeagents-judge-bench
+    name: "safeagents judge bench v0, test split, run on Apple M5 Pro (MPS)"