Instructions to use CalderaAI/30B-Lazarus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CalderaAI/30B-Lazarus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CalderaAI/30B-Lazarus")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("CalderaAI/30B-Lazarus") model = AutoModelForCausalLM.from_pretrained("CalderaAI/30B-Lazarus") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use CalderaAI/30B-Lazarus with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CalderaAI/30B-Lazarus" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CalderaAI/30B-Lazarus", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CalderaAI/30B-Lazarus
- SGLang
How to use CalderaAI/30B-Lazarus 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 "CalderaAI/30B-Lazarus" \ --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": "CalderaAI/30B-Lazarus", "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 "CalderaAI/30B-Lazarus" \ --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": "CalderaAI/30B-Lazarus", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CalderaAI/30B-Lazarus with Docker Model Runner:
docker model run hf.co/CalderaAI/30B-Lazarus
Licence
Hi, what is the licence for this model?
Every model used for the merge is downstream from Llama, so it would be the llama license.
Henk is correct, same as Llama model license. Research purposes only, not for commercial use. As ones research purpose may be subjective, it's not my place to gate that. This model was released on my call and is not representative of everyone in CalderaAI. As I put it to anyone who asks - I'm just a determined idiot with a keyboard who doesn't know when to quit. I hope you manage to find this model useful. I have an enormously better release than Laz coming. If you'd like, keep an eye out; it has no boundaries and is highly competent [33B-Epilogue is uploading...].
[Epilogue's small brother is Epsilon, turns out Epilogue is still in the works. Had some trouble with the 8K ctx making it spout gibberish on different setups, so I reverted to an old version of SuperHOT before the 8K release.]