Instructions to use Ba2han/muon-lora-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ba2han/muon-lora-2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Ba2han/test-model-muon")
model = PeftModel.from_pretrained(base_model, "Ba2han/muon-lora-2")

Transformers

How to use Ba2han/muon-lora-2 with Transformers:

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

pipe = pipeline("text-generation", model="Ba2han/muon-lora-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Ba2han/muon-lora-2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ba2han/muon-lora-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ba2han/muon-lora-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/muon-lora-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ba2han/muon-lora-2

SGLang

How to use Ba2han/muon-lora-2 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 "Ba2han/muon-lora-2" \
    --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": "Ba2han/muon-lora-2",
		"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 "Ba2han/muon-lora-2" \
        --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": "Ba2han/muon-lora-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Ba2han/muon-lora-2 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 Ba2han/muon-lora-2 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 Ba2han/muon-lora-2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ba2han/muon-lora-2 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Ba2han/muon-lora-2",
    max_seq_length=2048,
)

Docker Model Runner
How to use Ba2han/muon-lora-2 with Docker Model Runner:
```
docker model run hf.co/Ba2han/muon-lora-2
```

Model Card for Model ID

Model Details

Model Description

Developed by: Ba2han
Funded by [optional]: None
Model type: SLM
Language(s) (NLP): English, Turkish
License: MIT
Finetuned from model [optional]: Ba2han/test-model-muon

How to Get Started with the Model

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
from peft import PeftModel
import torch

BASE_MODEL_PATH = "Ba2han/test-model-muon"
LORA_PATH = "Ba2han/muon-lora-2"

model = AutoModelForCausalLM.from_pretrained(
    BASE_MODEL_PATH,
    device_map="auto",
    torch_dtype=torch.bfloat16,
    load_in_4bit=False,
    low_cpu_mem_usage=True,
)


tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL_PATH)
model = PeftModel.from_pretrained(model, LORA_PATH)

chat_pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    device_map="auto"
)

messages = [
    {"role": "system", "content": "Sen bir asistansın. Kısa ve doğru cevaplar ver."},
    {"role": "user", "content": "5+1 kaç eder?"},
]

# Convert to plain text for pipeline
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

# --- Generate ---
outputs = chat_pipe(
    prompt,
    max_new_tokens=256,
    temperature=0.62,
    top_p=0.95,
    top_k=16,
    repetition_penalty=1.05,
    do_sample=True
)

print(outputs[0]["generated_text"])

Output:

<|im_start|>system
Sen bir asistansın. Kısa ve doğru cevaplar ver.<|im_end|>
<|im_start|>user
5+1 kaç eder?<|im_end|>
<|im_start|>assistant
Adım 1: 5 ve 1 sayılarını toplamam gerekiyor.
Adım 2: 5 + 1 = 6.
Cevap: 6

Evaluation

Summary

Model Examination [optional]

[More Information Needed]

Downloads last month: 2

Model tree for Ba2han/muon-lora-2

Unable to build the model tree, the base model loops to the model itself. Learn more.