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, dtype="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
```

Mar2Ding commited on Mar 21, 2024

Commit

aeea885

verified ·

1 Parent(s): 25aecd2

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ We release SongComposer series in two versions:
 ### Import from Transformers
 To load the SongComposer_pretrain model using Transformers, use the following code:
 ```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
 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()
@@ -39,7 +39,7 @@ model.inference_pretrain(prompt, tokenizer, model)
 ### 通过 Transformers 加载
 通过以下的代码加载 SongComposer_pretrain 模型
 ```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
 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()

 ### Import from Transformers
 To load the SongComposer_pretrain model using Transformers, use the following code:
 ```python
+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()
 ### 通过 Transformers 加载
 通过以下的代码加载 SongComposer_pretrain 模型
 ```python
+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()