Instructions to use Henk717/airochronos-33B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Henk717/airochronos-33B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Henk717/airochronos-33B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Henk717/airochronos-33B") model = AutoModelForCausalLM.from_pretrained("Henk717/airochronos-33B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Henk717/airochronos-33B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Henk717/airochronos-33B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Henk717/airochronos-33B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Henk717/airochronos-33B
- SGLang
How to use Henk717/airochronos-33B 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 "Henk717/airochronos-33B" \ --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": "Henk717/airochronos-33B", "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 "Henk717/airochronos-33B" \ --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": "Henk717/airochronos-33B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Henk717/airochronos-33B with Docker Model Runner:
docker model run hf.co/Henk717/airochronos-33B
Prompt format for regular story writing
Hey, for KoboldAI (not lite) story writing, should I put an alpaca-format prompt in the memory box, or can I just write text in there? I'd assumed it was the latter, but I noticed in the description that you indicated it was tested for "regular story writing". Also, just out of curiosity, are "world info", etc. useful for any models other than KoboldAI's official models?
I tried that with the KoboldAI sample story which is just a regular story prompt.
But using Alpaca format in the memory box can help further guide it such as this:
### Instruction:
Write a story about a medieval kingdom tarnished by a Dragon. Our hero needs to be tasked to slay the dragon, on the way he encounters a group of bandits who turn out to be former heroes undercover.
### Response:
As for the world info question, these work on any model and help you manage the story context.
I had not tried that specific permutation of line spacing, I don't think, thanks. So does world info, then, just identify keywords and insert whatever text you put in? If so, does it insert it inline with the text before/after the keyword?