Instructions to use pi-dal/Linnaeus-0.1.0-2B-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pi-dal/Linnaeus-0.1.0-2B-merged with Transformers:

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

pipe = pipeline("image-text-to-text", model="pi-dal/Linnaeus-0.1.0-2B-merged")
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("pi-dal/Linnaeus-0.1.0-2B-merged")
model = AutoModelForMultimodalLM.from_pretrained("pi-dal/Linnaeus-0.1.0-2B-merged", 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 pi-dal/Linnaeus-0.1.0-2B-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pi-dal/Linnaeus-0.1.0-2B-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pi-dal/Linnaeus-0.1.0-2B-merged",
		"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/pi-dal/Linnaeus-0.1.0-2B-merged

SGLang

How to use pi-dal/Linnaeus-0.1.0-2B-merged 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 "pi-dal/Linnaeus-0.1.0-2B-merged" \
    --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": "pi-dal/Linnaeus-0.1.0-2B-merged",
		"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 "pi-dal/Linnaeus-0.1.0-2B-merged" \
        --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": "pi-dal/Linnaeus-0.1.0-2B-merged",
		"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 pi-dal/Linnaeus-0.1.0-2B-merged with Docker Model Runner:
```
docker model run hf.co/pi-dal/Linnaeus-0.1.0-2B-merged
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Linnaeus-0.1.0-2B — merged HF checkpoint

Linnaeus is a 2B decision model (classify/route/score arbitrary candidate sets from structured state). Fork of Dohnuts re-trained on Qwen3.5-2B. This repo contains the LoRA-merged full weights — no adapter loading needed.

Score-row trick

The scalar decision head is appended as an extra embed_tokens row (score_row_id = 248320, tied lm_head). For each candidate rendered with a <|fim_suffix|> marker, its decision score = logits[marker_pos, 248320]. Apply per-type temperature, softmax over candidates. Any stock LM runtime produces calibrated decision probabilities with zero custom head code.

Runtime contract: linnaeus-runtime.json (score_row_id, marker, temperatures).

Usage (torch, Mac MPS or any device)

from linnaeus.predictor import render_question  # prompt template
logits = model(**inputs).logits  # or last_hidden_state @ embed.T
score_i = logits[0, marker_pos_i, 248320]
probs = softmax(scores / temperature[qtype])

Measured (JevBench v1.2.2, 231 tasks): torch MPS 71.0%, CUDA reference 73.16%, upstream 65.8%. Conversion source for the MLX builds.