Instructions to use SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/root/.cache/huggingface/hub/models--zhaode--FastVLM-1.5B-Stage3/snapshots/13b83fd9ce0f45b187451909251353516717da7c")
model = PeftModel.from_pretrained(base_model, "SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5")

Transformers

How to use SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5")
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 AutoModel
model = AutoModel.from_pretrained("SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5",
		"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/SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5

SGLang

How to use SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5 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 "SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5" \
    --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": "SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5",
		"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 "SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5" \
        --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": "SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5",
		"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 SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5 with Docker Model Runner:
```
docker model run hf.co/SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5
```

FastVLM 1.5B - Meeting Tile v5 LoRA Adapter

LoRA adapter fine-tuned on FastVLM-1.5B-Stage3 for meeting screenshot analysis using a tile-crop strategy.

Tasks

Platform detection: Identify meeting platform (Zoom, Teams, Google Meet, Webex) from full screenshots
Tile name: Read participant name from an isolated tile crop
Tile speaker: Detect active speaker (highlighted border) + read name from a tile crop

Training Details

Base model: zhaode/FastVLM-1.5B-Stage3
Method: LoRA (rank=8, alpha=16) on language model q/k/v/o projections
Dataset: 103K synthetic examples (87.5K train / 15.5K val)
- 34K full screenshots (platform detection)
- 34K speaker tile crops (tile_speaker)
- 34K non-speaker tile crops (tile_name)
- 1K slide OCR examples
Training: 2 epochs, batch_size=8, grad_accum=2, lr=2e-5, cosine schedule
Hardware: NVIDIA A40 (46GB), ~4.5 hours
Final loss: ~0.10-0.12
Trainable params: 2.18M / 1.91B (0.11%)

Tile-Crop Strategy

Instead of asking the model to identify speakers from a full meeting screenshot (where name labels are ~13px after resize), we crop individual participant tiles and render them at full viewport (1280x720). This gives the model ~130px name labels -- a 10x improvement in readability.

Framework versions

PEFT 0.18.1
Transformers
PyTorch

Downloads last month: -

Model tree for SearchingBinary/FastVLM-1.5B-Stage3-meeting-tiles-v5

Base model

zhaode/FastVLM-1.5B-Stage3

Adapter

(3)

this model