Instructions to use Retreatcost/Limn-Alpha-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Retreatcost/Limn-Alpha-12B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Retreatcost/Limn-Alpha-12B")
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("Retreatcost/Limn-Alpha-12B")
model = AutoModelForMultimodalLM.from_pretrained("Retreatcost/Limn-Alpha-12B")
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 Retreatcost/Limn-Alpha-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Retreatcost/Limn-Alpha-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Retreatcost/Limn-Alpha-12B",
		"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/Retreatcost/Limn-Alpha-12B

SGLang

How to use Retreatcost/Limn-Alpha-12B 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 "Retreatcost/Limn-Alpha-12B" \
    --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": "Retreatcost/Limn-Alpha-12B",
		"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 "Retreatcost/Limn-Alpha-12B" \
        --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": "Retreatcost/Limn-Alpha-12B",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Studio

How to use Retreatcost/Limn-Alpha-12B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Retreatcost/Limn-Alpha-12B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Retreatcost/Limn-Alpha-12B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Retreatcost/Limn-Alpha-12B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Retreatcost/Limn-Alpha-12B",
    max_seq_length=2048,
)

Docker Model Runner
How to use Retreatcost/Limn-Alpha-12B with Docker Model Runner:
```
docker model run hf.co/Retreatcost/Limn-Alpha-12B
```

Limn-Alpha-12B

A generalist finetune, more vivid language and different thinking patterns.

I've transplanted lm_head from Gryphe/Gemma-4-12B-StyleTune to uncensored base llmfan46/gemma-4-12B-it-uncensored-heretic and did an rsLoRA finetuning on top.

After a brief testing it seems that both audio and video capabilites have been preserved, in some cases outputs are even more descriptive.

Inference Tips

Temperature: 1.0
TOP_P: 0.95
TOP_K: 0 (disable)
MIN_P: 0.025
Template Format: Gemma4

Both thinking and non-thinking works.

These settings are practically the same as official recommendations, but i found to like MinP better than TopK.

Training details

Spoiler warning

Trained on same dataset as Evertide-RX-12B.

Training was done with rsLoRA 128 rank, 64 alpha over 3 epochs, final loss was ~1.22.

During training o_proj was omitted to preserve uncensoring from heretic base model.

Special Thanks

Gryphe Padar: for his cool StyleTune idea and model (and all other cool tunes he done).
LLMfan46 for his never-ending flow of high-quality herectic models.

Future Plans

This is an "Alpha" tune, that turned out to be quite good in my opinion. Probably going to do an FFT with better sample composition and extended dataset.