Instructions to use webbrain-one/lfm3-vld-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use webbrain-one/lfm3-vld-2b with Transformers:

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

pipe = pipeline("image-text-to-text", model="webbrain-one/lfm3-vld-2b", 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 AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("webbrain-one/lfm3-vld-2b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use webbrain-one/lfm3-vld-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "webbrain-one/lfm3-vld-2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "webbrain-one/lfm3-vld-2b",
		"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/webbrain-one/lfm3-vld-2b

SGLang

How to use webbrain-one/lfm3-vld-2b 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 "webbrain-one/lfm3-vld-2b" \
    --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": "webbrain-one/lfm3-vld-2b",
		"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 "webbrain-one/lfm3-vld-2b" \
        --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": "webbrain-one/lfm3-vld-2b",
		"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 webbrain-one/lfm3-vld-2b with Docker Model Runner:
```
docker model run hf.co/webbrain-one/lfm3-vld-2b
```

webbrain-one commited on 1 day ago

Commit

fbe2e60

verified ·

1 Parent(s): c0c2db9

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -17,9 +17,9 @@ tags:
 - custom_code
 ---
-# LFM3-VL-2B-VLDR
-`LFM3-VL-2B-VLDR` (Restored Language Head) is a hybrid multimodal browser decision model built using the **Pegasus method** (inspired by `AveLabs/Qwen3.8-27B-Perplexing-Pegasus`).
 It combines:
 1. **Decision Backbone**: The complete 24-layer hybrid architecture (Conv + GQA attention + Feed-Forward), vision tower, multimodal projector, and embeddings from `LiquidAI/d1-2B` (trained on browser actions, verification, and decision trajectories).
@@ -35,8 +35,8 @@ When models like `LiquidAI/d1-2B` undergo full fine-tuning on decision tasks wit
 | Model / Method | Accuracy | Completion Found | False Completions | Unknown Recognized |
 |---|---:|---:|---:|---:|
-| **LFM3-VL-2B-VLDR (Decision Probe)** | **115/126 (91.3%)** | **24/24 (100%)** | **0/48 (0%)** | **24/24 (100%)** |
-| **LFM3-VL-2B-VLDR (`verify` Zero-Shot)** | **85/126 (67.5%)** | **22/24 (91.7%)** | **0/48 (0%)** | **0/24 (0%)** |
 | LFM3-VL-2B-VLD (LoRA Distillation) | 126/126 (100.0%) | 24/24 (100%) | 0/48 (0%) | 24/24 (100%) |
 | Base `LiquidAI/LFM3-VL-2B` (`verify` Zero-Shot) | 106/126 (84.1%) | 24/24 (100%) | 0/48 (0%) | 4/24 (16.7%) |

 - custom_code
 ---
+# LFM3-VLD-2B
+`LFM3-VLD-2B` (Restored Language Head) is a hybrid multimodal browser decision model built using the **Pegasus method** (inspired by `AveLabs/Qwen3.8-27B-Perplexing-Pegasus`).
 It combines:
 1. **Decision Backbone**: The complete 24-layer hybrid architecture (Conv + GQA attention + Feed-Forward), vision tower, multimodal projector, and embeddings from `LiquidAI/d1-2B` (trained on browser actions, verification, and decision trajectories).
 | Model / Method | Accuracy | Completion Found | False Completions | Unknown Recognized |
 |---|---:|---:|---:|---:|
+| **LFM3-VLD-2B (Decision Probe)** | **115/126 (91.3%)** | **24/24 (100%)** | **0/48 (0%)** | **24/24 (100%)** |
+| **LFM3-VLD-2B (`verify` Zero-Shot)** | **85/126 (67.5%)** | **22/24 (91.7%)** | **0/48 (0%)** | **0/24 (0%)** |
 | LFM3-VL-2B-VLD (LoRA Distillation) | 126/126 (100.0%) | 24/24 (100%) | 0/48 (0%) | 24/24 (100%) |
 | Base `LiquidAI/LFM3-VL-2B` (`verify` Zero-Shot) | 106/126 (84.1%) | 24/24 (100%) | 0/48 (0%) | 4/24 (16.7%) |