Instructions to use IkariDev/Athena-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IkariDev/Athena-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="IkariDev/Athena-v3")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("IkariDev/Athena-v3") model = AutoModelForCausalLM.from_pretrained("IkariDev/Athena-v3") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use IkariDev/Athena-v3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IkariDev/Athena-v3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IkariDev/Athena-v3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/IkariDev/Athena-v3
- SGLang
How to use IkariDev/Athena-v3 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 "IkariDev/Athena-v3" \ --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": "IkariDev/Athena-v3", "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 "IkariDev/Athena-v3" \ --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": "IkariDev/Athena-v3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use IkariDev/Athena-v3 with Docker Model Runner:
docker model run hf.co/IkariDev/Athena-v3
Thanks and questions
@IkariDev and @Undi95 you guys are beasts! I've just started trying (and enjoying) Athena v2 and you already released v3 π. I really appreciate the efforts you've put into these models!
I also have some questions, hopefully you guys can help answer them:
- Should I use the recommended settings by localfultonextractor in v2's description for v3?
- I'm using SillyTavern v1.10.4 with the default Advanced Formatting settings ("Default" context template, instruct mode disabled), do you think using these settings instead would improve Athena's conversation quality? I'll try them out and see for myself, but I'd love to have your opinions too :)
- Is there a Discord I can join to follow your development and feedback from other users?
Thank you so much for your feedback, i really appriciate it! I'll send you the answers to all that when im home again(should be in around 6 hours).
- IkariDev :)
- ill put recommended settings in the repo in a couple of hours, try what works best for you.
- i always suggest using the "roleplay" advanced formatting preset, + instruct same, and enabled.
- Not really, but i am mainly active on the dc servers thebloke(character-roleplay-stories) and sillytavern(local-llm-chat).
I would be happy to see you over there. Thanks again for your feedback!
Thank you for your answers! I'll take a look at those Discord servers. Cheers!