Instructions to use Mar2Ding/songcomposer_pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mar2Ding/songcomposer_pretrain with Transformers:

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

pipe = pipeline("text-generation", model="Mar2Ding/songcomposer_pretrain", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Mar2Ding/songcomposer_pretrain", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mar2Ding/songcomposer_pretrain with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mar2Ding/songcomposer_pretrain"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mar2Ding/songcomposer_pretrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mar2Ding/songcomposer_pretrain

SGLang

How to use Mar2Ding/songcomposer_pretrain 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 "Mar2Ding/songcomposer_pretrain" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mar2Ding/songcomposer_pretrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Mar2Ding/songcomposer_pretrain" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mar2Ding/songcomposer_pretrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Mar2Ding/songcomposer_pretrain with Docker Model Runner:
```
docker model run hf.co/Mar2Ding/songcomposer_pretrain
```

songcomposer_pretrain / README.md

Mar2Ding

Update README.md

495ac2e verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

2.33 kB

metadata

license: apache-2.0
pipeline_tag: text-generation

[ACL 2025] SongComposer

💻Github Repo

📖Paper

SongComposer is a language large model (LLM) based on InternLM2 for lyric and melody composition in song generation.

We release SongComposer series in two versions:

SongComposer_pretrain: The pretrained SongComposer with InternLM2 as the initialization of the LLM, gains basic knowledge of lyric and melody.
SongComposer_sft: The finetuned SongComposer for instruction-following song generation including lyric to melody, melody to lyric, song continuation, text to song.

Import from Transformers

To load the SongComposer_pretrain model using Transformers, use the following code:

from transformers import AutoTokenizer, AutoModel
ckpt_path = "Mar2Ding/songcomposer_pretrain"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True)
model = AutoModel.from_pretrained(ckpt_path, trust_remote_code=True).cuda().half()
prompt = '<bop> Total 7 lines. The first line:可,<D4>,<137>,<79>|惜,<D#4>,<137>,<79>|这,<F4>,<137>,<88>|是,<F4>,<121>,<79>|属,<F4>,<121>,<79>|于,<D#4>,<214>,<88>|你,<D#4>,<141>,<79>|的,<D4>,<130>,<79>|风,<C4>,<151>,<79>|景,<A#3> <F3>,<181><137>,<79>\n'
model.inference_pretrain(prompt, tokenizer)

通过 Transformers 加载

通过以下的代码加载 SongComposer_pretrain 模型

from transformers import AutoTokenizer, AutoModel
ckpt_path = "Mar2Ding/songcomposer_pretrain"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True)
model = AutoModel.from_pretrained(ckpt_path, trust_remote_code=True).cuda().half()
prompt = '<bop> Total 7 lines. The first line:可,<D4>,<137>,<79>|惜,<D#4>,<137>,<79>|这,<F4>,<137>,<88>|是,<F4>,<121>,<79>|属,<F4>,<121>,<79>|于,<D#4>,<214>,<88>|你,<D#4>,<141>,<79>|的,<D4>,<130>,<79>|风,<C4>,<151>,<79>|景,<A#3> <F3>,<181><137>,<79>\n'
model.inference_pretrain(prompt, tokenizer)

Open Source License

The code is licensed under Apache-2.0, while model weights are fully open for academic research and also allow free commercial usage.