Instructions to use DancingIguana/music-generation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DancingIguana/music-generation with Transformers:

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

pipe = pipeline("text-generation", model="DancingIguana/music-generation")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DancingIguana/music-generation")
model = AutoModelForCausalLM.from_pretrained("DancingIguana/music-generation", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DancingIguana/music-generation with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DancingIguana/music-generation

SGLang

How to use DancingIguana/music-generation 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 "DancingIguana/music-generation" \
    --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": "DancingIguana/music-generation",
		"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 "DancingIguana/music-generation" \
        --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": "DancingIguana/music-generation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DancingIguana/music-generation with Docker Model Runner:
```
docker model run hf.co/DancingIguana/music-generation
```

@@ -42,5 +42,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.19.4",
   "use_cache": true,
-  "vocab_size": 19627
 }

   "torch_dtype": "float32",
   "transformers_version": "4.19.4",
   "use_cache": true,
+  "vocab_size": 25000
 }

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc4daea4da48a8f8527ce3188299fbed7a5ce73cc2abd63911356a0ae86bb8c
-size 239873757

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfe0d6f28d548682a6a7fdbcee77db1b51e7e18d538172d0ad182699ddcc5aba
 size 3183

DancingIguana
/

music-generation

End of training

 version https://git-lfs.github.com/spec/v1
+oid sha256:99f27a5a364382d51c51c5b7931a326b67a3e16b8ea3d6e3039050478f2ba764
+size 256379613

+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe176bd2644823a765763c5c473445a0dec05263afbda8cddd1c29456ff7016
+size 5159

+version https://git-lfs.github.com/spec/v1
+oid sha256:b0aff68a29178539b87713666fcea19f2257934f3707b0694e02bd4d693328bb
+size 3845

+version https://git-lfs.github.com/spec/v1
+oid sha256:5625eed6297396566abf334139e2a88a8fd8cf5a50a88e78dd5bc2b5f96306fb
+size 4199

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@