Instructions to use Tet0Kasane/Lumi-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tet0Kasane/Lumi-V2 with Transformers:

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

pipe = pipeline("text-generation", model="Tet0Kasane/Lumi-V2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tet0Kasane/Lumi-V2")
model = AutoModelForCausalLM.from_pretrained("Tet0Kasane/Lumi-V2", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tet0Kasane/Lumi-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tet0Kasane/Lumi-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tet0Kasane/Lumi-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tet0Kasane/Lumi-V2

SGLang

How to use Tet0Kasane/Lumi-V2 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 "Tet0Kasane/Lumi-V2" \
    --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": "Tet0Kasane/Lumi-V2",
		"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 "Tet0Kasane/Lumi-V2" \
        --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": "Tet0Kasane/Lumi-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Tet0Kasane/Lumi-V2 with Docker Model Runner:
```
docker model run hf.co/Tet0Kasane/Lumi-V2
```

Lumi-V2

Fine-tuned version of Qwen2.5-7B-Instruct with a sassy personality.

Model Details

Base Model: Qwen2.5-7B-Instruct
Training: Fine-tuned with Unsloth
Format: ChatML

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Tet0Kasane/Lumi-V2")
tokenizer = AutoTokenizer.from_pretrained("Tet0Kasane/Lumi-V2")

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=128)
response = tokenizer.batch_decode(outputs)[0]
print(response)

ChatML Format

This model uses the ChatML format:

<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
Hello!<|im_end|>
<|im_start|>assistant

Trained with Unsloth: https://github.com/unslothai/unsloth

Downloads last month: 2

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Tet0Kasane/Lumi-V2

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

unsloth/Qwen2.5-7B-Instruct-bnb-4bit

Finetuned

(294)

this model