Instructions to use BreadAi/MuseCan with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BreadAi/MuseCan with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BreadAi/MuseCan")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BreadAi/MuseCan") model = AutoModelForCausalLM.from_pretrained("BreadAi/MuseCan") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BreadAi/MuseCan with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BreadAi/MuseCan" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BreadAi/MuseCan", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BreadAi/MuseCan
- SGLang
How to use BreadAi/MuseCan 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 "BreadAi/MuseCan" \ --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": "BreadAi/MuseCan", "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 "BreadAi/MuseCan" \ --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": "BreadAi/MuseCan", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BreadAi/MuseCan with Docker Model Runner:
docker model run hf.co/BreadAi/MuseCan
Adding Evaluation Results
#2
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -21,4 +21,17 @@ The Future of MuseCan
|
|
| 21 |
MuseCan is still under development, but it has the potential to be a powerful tool for music generation. In the future, MuseCan could be used to create music that is even more realistic and lifelike. It could also be used to create music that is tailored to specific individuals. For example, MuseCan could be used to create a song that is specifically for a person's birthday or anniversary.
|
| 22 |
|
| 23 |
Conclusion
|
| 24 |
-
MuseCan is a powerful tool that can be used to generate a variety of musical styles. It can be used to generate music for a variety of purposes, such as for video games, movies, or simply for personal enjoyment. MuseCan is still under development, but it has the potential to be a powerful tool for music generation.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
MuseCan is still under development, but it has the potential to be a powerful tool for music generation. In the future, MuseCan could be used to create music that is even more realistic and lifelike. It could also be used to create music that is tailored to specific individuals. For example, MuseCan could be used to create a song that is specifically for a person's birthday or anniversary.
|
| 22 |
|
| 23 |
Conclusion
|
| 24 |
+
MuseCan is a powerful tool that can be used to generate a variety of musical styles. It can be used to generate music for a variety of purposes, such as for video games, movies, or simply for personal enjoyment. MuseCan is still under development, but it has the potential to be a powerful tool for music generation.
|
| 25 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 26 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_BreadAi__MuseCan)
|
| 27 |
+
|
| 28 |
+
| Metric | Value |
|
| 29 |
+
|-----------------------|---------------------------|
|
| 30 |
+
| Avg. | 18.06 |
|
| 31 |
+
| ARC (25-shot) | 28.07 |
|
| 32 |
+
| HellaSwag (10-shot) | 25.0 |
|
| 33 |
+
| MMLU (5-shot) | 24.19 |
|
| 34 |
+
| TruthfulQA (0-shot) | 0.0 |
|
| 35 |
+
| Winogrande (5-shot) | 49.09 |
|
| 36 |
+
| GSM8K (5-shot) | 0.0 |
|
| 37 |
+
| DROP (3-shot) | 0.03 |
|