Instructions to use digitous/Javelin-GPTJ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use digitous/Javelin-GPTJ with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="digitous/Javelin-GPTJ")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("digitous/Javelin-GPTJ") model = AutoModelForCausalLM.from_pretrained("digitous/Javelin-GPTJ") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use digitous/Javelin-GPTJ with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "digitous/Javelin-GPTJ" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "digitous/Javelin-GPTJ", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/digitous/Javelin-GPTJ
- SGLang
How to use digitous/Javelin-GPTJ 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 "digitous/Javelin-GPTJ" \ --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": "digitous/Javelin-GPTJ", "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 "digitous/Javelin-GPTJ" \ --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": "digitous/Javelin-GPTJ", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use digitous/Javelin-GPTJ with Docker Model Runner:
docker model run hf.co/digitous/Javelin-GPTJ
Javelin-GPTJ is an even 25*4 quad merge of KoboldAI's GPT-J classics;
(Janeway + Shinen) + (Adventure + Skein). Janeway + Shinen is listed under JANIN-GPTJ. Adventure + Skein is listed under Adventien-GPTJ.
Original models can all be found under KoboldAI.
This 4x merge is not intended for minors, as it can produce NC-17+ content (mostly from Shinen).
GPT-R merge variant will be released if it adds value to this already "kitchen sink" level of merging.
- Downloads last month
- 1,134