Instructions to use EleutherAI/gpt-j-6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EleutherAI/gpt-j-6b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="EleutherAI/gpt-j-6b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-j-6b") model = AutoModelForCausalLM.from_pretrained("EleutherAI/gpt-j-6b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use EleutherAI/gpt-j-6b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "EleutherAI/gpt-j-6b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "EleutherAI/gpt-j-6b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/EleutherAI/gpt-j-6b
- SGLang
How to use EleutherAI/gpt-j-6b 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 "EleutherAI/gpt-j-6b" \ --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": "EleutherAI/gpt-j-6b", "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 "EleutherAI/gpt-j-6b" \ --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": "EleutherAI/gpt-j-6b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use EleutherAI/gpt-j-6b with Docker Model Runner:
docker model run hf.co/EleutherAI/gpt-j-6b
rust_weights
Add rust_model.ot model weights.
This is particularly of use for GPT-J implementation in Rust.
See related PR
Besides, I'd like to add the rust weights for the float16 version too, however I am not sure how to create a PR that uses refs/heads/float16 as a base.
I tried to do it in pr 6, but it doesn't seem to work.
Do you have any clue on that ?
@stellaathena @juliensimon Just pinging you as I am not sure whether you get notifications when a PR is opened (If you do, sorry for the spam !)
At this time we are unable to accept outside PRs that change the model in any way.