Instructions to use Tremontaine/L3-12B-Lunaris-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tremontaine/L3-12B-Lunaris-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Tremontaine/L3-12B-Lunaris-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tremontaine/L3-12B-Lunaris-v1")
model = AutoModelForCausalLM.from_pretrained("Tremontaine/L3-12B-Lunaris-v1", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tremontaine/L3-12B-Lunaris-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tremontaine/L3-12B-Lunaris-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tremontaine/L3-12B-Lunaris-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tremontaine/L3-12B-Lunaris-v1

SGLang

How to use Tremontaine/L3-12B-Lunaris-v1 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 "Tremontaine/L3-12B-Lunaris-v1" \
    --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": "Tremontaine/L3-12B-Lunaris-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Tremontaine/L3-12B-Lunaris-v1" \
        --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": "Tremontaine/L3-12B-Lunaris-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Tremontaine/L3-12B-Lunaris-v1 with Docker Model Runner:
```
docker model run hf.co/Tremontaine/L3-12B-Lunaris-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

L3-12B-Lunaris-v1

L3-12B-Lunaris-v1 is a self merge of the following model using LazyMergekit with --clone-tensors argument added:

Sao10K/L3-8B-Lunaris-v1

Works best with lower temperature, between 0.8-0.9.

🧩 Configuration

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 8]
    model: Sao10K/L3-8B-Lunaris-v1
    parameters:
      scale_rules:
      - filter: value
        value: 0.8
- sources:
  - layer_range: [8, 16]
    model: Sao10K/L3-8B-Lunaris-v1
    parameters:
      scale_rules:
      - filter: value
        value: 0.8
- sources:
  - layer_range: [16, 24]
    model: Sao10K/L3-8B-Lunaris-v1
    parameters:
      scale_rules:
      - filter: value
        value: 1.0
- sources:
  - layer_range: [24, 32]
    model: Sao10K/L3-8B-Lunaris-v1
    parameters:
      scale_rules:
      - filter: value
        value: 1.0
- sources:
  - layer_range: [0, 8]
    model: Sao10K/L3-8B-Lunaris-v1
    parameters:
      scale_rules:
      - filter: value
        value: 0.7
- sources:
  - layer_range: [8, 16]
    model: Sao10K/L3-8B-Lunaris-v1
    parameters:
      scale_rules:
      - filter: value
        value: 0.7

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Tremontaine/L3-12B-Lunaris-v1"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	25.38
IFEval (0-Shot)	69.09
BBH (3-Shot)	32.18
MATH Lvl 5 (4-Shot)	8.16
GPQA (0-shot)	7.94
MuSR (0-shot)	4.05
MMLU-PRO (5-shot)	30.83

Downloads last month: 30

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for Tremontaine/L3-12B-Lunaris-v1

Base model

Sao10K/L3-8B-Lunaris-v1

Finetuned

(4)

this model

Quantizations

2 models

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

69.090
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

32.180
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

8.160
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

7.940
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

4.050
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

30.830