Instructions to use digitous/Alpacino30b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use digitous/Alpacino30b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="digitous/Alpacino30b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("digitous/Alpacino30b") model = AutoModelForCausalLM.from_pretrained("digitous/Alpacino30b") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use digitous/Alpacino30b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "digitous/Alpacino30b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "digitous/Alpacino30b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/digitous/Alpacino30b
- SGLang
How to use digitous/Alpacino30b 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 "digitous/Alpacino30b" \ --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": "digitous/Alpacino30b", "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 "digitous/Alpacino30b" \ --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": "digitous/Alpacino30b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use digitous/Alpacino30b with Docker Model Runner:
docker model run hf.co/digitous/Alpacino30b
Have you seen the "Guanaco" model?
https://huggingface.co/JosephusCheung/Guanaco
Instruction:
User: History User Input
Assistant: History Assistant Answer
Input:
System: Knowledge
User: New User Input
Response:
New Assistant Answer
It's multi-shot. I'm new to this stuff, so I doubt I have a firm grasp on how to best utilize this for e.g. AlPacino's use cases (various species of narrative/story writing), but I figured I'd forward it to you in case you hadn't seen it. Doesn't KoboldAI have hooks for memory or summarization or something?
Seems like it would be fairly easy to leverage this to improve the cogency of a narrative.