Instructions to use starmpcc/Asclepius-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use starmpcc/Asclepius-13B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="starmpcc/Asclepius-13B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("starmpcc/Asclepius-13B") model = AutoModelForCausalLM.from_pretrained("starmpcc/Asclepius-13B") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use starmpcc/Asclepius-13B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "starmpcc/Asclepius-13B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "starmpcc/Asclepius-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/starmpcc/Asclepius-13B
- SGLang
How to use starmpcc/Asclepius-13B 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 "starmpcc/Asclepius-13B" \ --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": "starmpcc/Asclepius-13B", "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 "starmpcc/Asclepius-13B" \ --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": "starmpcc/Asclepius-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use starmpcc/Asclepius-13B with Docker Model Runner:
docker model run hf.co/starmpcc/Asclepius-13B
Tokenizer is missing
Hi
Thanks for the interesting new model! I'm going to quantize it and help more people find out about it.
You're missing all the tokenizer files from your repo - tokenizer.json, tokenizer.model, tokenizer_config.json.
For my quantisations I have grabbed the files from huggyllama/llama-13b. I could PR them here, but I thought it'd be better if you added them, just in case you've customised them in any way?
Thanks!
PS. Any plans to train this on Llama 2?
Thank you for notifying us of the bug.
We have immediately added the necessary tokenizer-related files.
We are currently considering to update with LLaMA-2, but we don't have a schedule for it yet.
Thank you!