Instructions to use vectionlabs/Salience-27B-R4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vectionlabs/Salience-27B-R4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="vectionlabs/Salience-27B-R4")
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("vectionlabs/Salience-27B-R4")
model = AutoModelForMultimodalLM.from_pretrained("vectionlabs/Salience-27B-R4", 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 vectionlabs/Salience-27B-R4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vectionlabs/Salience-27B-R4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vectionlabs/Salience-27B-R4",
		"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/vectionlabs/Salience-27B-R4

SGLang

How to use vectionlabs/Salience-27B-R4 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 "vectionlabs/Salience-27B-R4" \
    --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": "vectionlabs/Salience-27B-R4",
		"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 "vectionlabs/Salience-27B-R4" \
        --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": "vectionlabs/Salience-27B-R4",
		"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 vectionlabs/Salience-27B-R4 with Docker Model Runner:
```
docker model run hf.co/vectionlabs/Salience-27B-R4
```

Benchmarks?

by je0923 - opened 13 days ago

Discussion

je0923

13 days ago

Can we get some benchmarks? I want to compare to base Qwen and DavidAU's 711!

EdwardForReal

12 days ago

Ok! We'll add to the readme some benchmarks for comparing this with other models! Would you like a specific type of benchmarks or the most known?

je0923

12 days ago

Hmm, whatever is the most known :) But the best for me personally would be agentic coding! I am curious about your other salience model's benchmarks too!

Thank you so much <3

vectionlabs

Owner 2 days ago

@je0923 Please excuse the delay in adding the benchmarks; we needed to save some checkpoints and analyze the weights for Salience-R5 (based on Qwen3.8-27B). We wanted to let you know that we are about to run the benchmark scripts and add the results to the README.md. As a team member, I would like to personally ask what issues you encountered with Salience-R4, so we can try to fix them in R5. Thank you very much!

je0923

2 days ago

@vectionlabs no worries!! and unfortunately i still havent gotten around to trying it yet 💀

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment