Instructions to use elinas/chronos-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use elinas/chronos-13b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="elinas/chronos-13b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("elinas/chronos-13b") model = AutoModelForCausalLM.from_pretrained("elinas/chronos-13b") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use elinas/chronos-13b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "elinas/chronos-13b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "elinas/chronos-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/elinas/chronos-13b
- SGLang
How to use elinas/chronos-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 "elinas/chronos-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": "elinas/chronos-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 "elinas/chronos-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": "elinas/chronos-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use elinas/chronos-13b with Docker Model Runner:
docker model run hf.co/elinas/chronos-13b
Dataset?
Out of curiosity, what was the dataset this was trained on?
A compilation of chat datasets from different sources with some WizardLM mixed in.
Any chance you will donate the dataset to community. Very interested to try this dataset on OpenLLaMA models and release to community.
Honestly, the Chronos finetunes have been the best rp chat I've had so far, and also work very well as part of model merges.
@elinas sharing the recipe would be so valuable for further advances, especially now that llama2 is out for finetuning.
It won't be shared due to the sources. Feel free to merge the model. v2 is coming.
ok, understood, thanks for the work for community, much appreciated :)