Instructions to use architext/gptj-162M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use architext/gptj-162M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="architext/gptj-162M")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("architext/gptj-162M") model = AutoModelForCausalLM.from_pretrained("architext/gptj-162M") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use architext/gptj-162M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "architext/gptj-162M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "architext/gptj-162M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/architext/gptj-162M
- SGLang
How to use architext/gptj-162M 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 "architext/gptj-162M" \ --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": "architext/gptj-162M", "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 "architext/gptj-162M" \ --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": "architext/gptj-162M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use architext/gptj-162M with Docker Model Runner:
docker model run hf.co/architext/gptj-162M
Runtime Error
Hello,
Every time I try to use the model I get the following error.
RuntimeError: The size of tensor a (48) must match the size of tensor b (64) at non-singleton dimension 3
It happens also on the huggingface page in the test section of the model page.
I am new to ML, but to me it looks like internal problem that a model encounters when trying to parse the input I feed to it. This is an example string I use as input.
a house with two bedrooms and three bathrooms
I appreciate any ideas how one can fix this on the user side or any updates about possible fixes in the future =)
hello , greetings
Iam facing the same issue if you have resolved can you please share the steps to overcome this error.
you need to change to "rotary_dim": 48 in config.json.
The model performed very bad. I doubt that their experiments are reproducible.