Text Generation
Transformers
PyTorch
Safetensors
English
llama
alpaca
vicuna
uncensored
Merge
mix
airoboros
openorca
orcamini
orca
instruct
mixtune
text-generation-inference
Instructions to use CalderaAI/13B-Ouroboros with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CalderaAI/13B-Ouroboros with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CalderaAI/13B-Ouroboros")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("CalderaAI/13B-Ouroboros") model = AutoModelForCausalLM.from_pretrained("CalderaAI/13B-Ouroboros") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use CalderaAI/13B-Ouroboros with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CalderaAI/13B-Ouroboros" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CalderaAI/13B-Ouroboros", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CalderaAI/13B-Ouroboros
- SGLang
How to use CalderaAI/13B-Ouroboros 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/13B-Ouroboros" \ --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/13B-Ouroboros", "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/13B-Ouroboros" \ --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/13B-Ouroboros", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CalderaAI/13B-Ouroboros with Docker Model Runner:
docker model run hf.co/CalderaAI/13B-Ouroboros
Ouroboros vs Bluemethod
#1
by Hoioi - opened
Which of the Ouroboros and Bluemethod perform better in article writing ? Is there any benchmark regarding these two models?
Personally I'd presume Ouroboros would be, as it was directly compared against the PTB dataset for every step of the merge process, PTB's dataset is one of the better quality datasets out there for English written language.
Did you train Ouroboros on full openorca database which is about 4.2 million rows?
Ouroboros is a merged model, and he merged from orca_mini