Text Generation
Transformers
PyTorch
Safetensors
Hungarian
English
Chinese
gpt_neox
puli
text-generation-inference
Instructions to use NYTK/PULI-GPTrio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NYTK/PULI-GPTrio with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="NYTK/PULI-GPTrio")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("NYTK/PULI-GPTrio") model = AutoModelForCausalLM.from_pretrained("NYTK/PULI-GPTrio", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use NYTK/PULI-GPTrio with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NYTK/PULI-GPTrio" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NYTK/PULI-GPTrio", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/NYTK/PULI-GPTrio
- SGLang
How to use NYTK/PULI-GPTrio 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 "NYTK/PULI-GPTrio" \ --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": "NYTK/PULI-GPTrio", "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 "NYTK/PULI-GPTrio" \ --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": "NYTK/PULI-GPTrio", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use NYTK/PULI-GPTrio with Docker Model Runner:
docker model run hf.co/NYTK/PULI-GPTrio
Oobabooga
#2
by mp3pintyo - opened
I tried to use it on Oobabooga's interface in Hungarian, but I did not manage to generate an output like the PULI-GPTrio demo page at all.
With what settings should it be used?
Dear mp3pintyo, this model on Huggingface is the raw pretrained language model. On our demo page you can find the fine-tuned (using Stanford Alpaca) instruct model. We did not publish the fine-tuned model.
Thanks for the reply.