Instructions to use asigalov61/Karaoke-Lyrics-Qwen3-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use asigalov61/Karaoke-Lyrics-Qwen3-0.6B with Transformers:

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

pipe = pipeline("text-generation", model="asigalov61/Karaoke-Lyrics-Qwen3-0.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("asigalov61/Karaoke-Lyrics-Qwen3-0.6B")
model = AutoModelForCausalLM.from_pretrained("asigalov61/Karaoke-Lyrics-Qwen3-0.6B", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use asigalov61/Karaoke-Lyrics-Qwen3-0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "asigalov61/Karaoke-Lyrics-Qwen3-0.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "asigalov61/Karaoke-Lyrics-Qwen3-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/asigalov61/Karaoke-Lyrics-Qwen3-0.6B

SGLang

How to use asigalov61/Karaoke-Lyrics-Qwen3-0.6B 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 "asigalov61/Karaoke-Lyrics-Qwen3-0.6B" \
    --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": "asigalov61/Karaoke-Lyrics-Qwen3-0.6B",
		"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 "asigalov61/Karaoke-Lyrics-Qwen3-0.6B" \
        --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": "asigalov61/Karaoke-Lyrics-Qwen3-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use asigalov61/Karaoke-Lyrics-Qwen3-0.6B with Docker Model Runner:
```
docker model run hf.co/asigalov61/Karaoke-Lyrics-Qwen3-0.6B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Karaoke Lyrics Qwen3 0.6B

Lyrics template to lyrics model for Orpheus Karaoke

Model was post-trained on ~500k randomly selected clean lyrics-template pairs

How to use

Load the model

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "asigalov61/Karaoke-Lyrics-Qwen3-0.6B"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

Generate

lyrics = "So close no matter how far\nCould not be much more from the heart\nForever trusting who we are\nAnd nothing else matters"

prompt = 'Lyrics template: ' + ' '.join(['_' * len(w) for w in lyrics.split()])

messages = [
    {"role": "system", "content": "Please fill in the words in the following song lyrics template and guess song title. Thank you."},
    {"role": "user", "content": prompt}
]

chat_text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False
)

model_inputs = tokenizer([chat_text], return_tensors="pt").to(model.device)

num_batches = 1

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.9,
    top_p=0.96,
    top_k=2,
    num_return_sequences=num_batches,
    repetition_penalty=1.05
)

output_tokens = [
    output_ids[len(input_ids):]
    for input_ids, output_ids in zip([model_inputs.input_ids] * num_batches, generated_ids)
]

responses = tokenizer.batch_decode(output_tokens, skip_special_tokens=True)

final_responses = []

for r in responses:
    final_responses.append(r.split('\n</think>\n')[-1].strip())

print(final_responses[0])

Project Los Angeles

Tegridy Code 2026

Downloads last month: 9

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for asigalov61/Karaoke-Lyrics-Qwen3-0.6B

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

(1069)

this model

Quantizations

1 model

asigalov61
/

Karaoke-Lyrics-Qwen3-0.6B