Instructions to use DAMO-NLP-MT/polylm-1.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DAMO-NLP-MT/polylm-1.7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DAMO-NLP-MT/polylm-1.7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DAMO-NLP-MT/polylm-1.7b") model = AutoModelForCausalLM.from_pretrained("DAMO-NLP-MT/polylm-1.7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use DAMO-NLP-MT/polylm-1.7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DAMO-NLP-MT/polylm-1.7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DAMO-NLP-MT/polylm-1.7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/DAMO-NLP-MT/polylm-1.7b
- SGLang
How to use DAMO-NLP-MT/polylm-1.7b 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 "DAMO-NLP-MT/polylm-1.7b" \ --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": "DAMO-NLP-MT/polylm-1.7b", "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 "DAMO-NLP-MT/polylm-1.7b" \ --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": "DAMO-NLP-MT/polylm-1.7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use DAMO-NLP-MT/polylm-1.7b with Docker Model Runner:
docker model run hf.co/DAMO-NLP-MT/polylm-1.7b
I'd like to use the performance for polylm-1.7b
#1
by yspaik - opened
https://arxiv.org/pdf/2307.06018.pdf
I saw your models in the paper above. First of all, thank you for revealing the wonderful models. I know that you opened 1.7b and 13b, but in the case of 13b, detailed specifications including config are posted along with the binary, but when I tried to use 1.7b, there was no accurate information. I would like to know when it will be posted.
Thanks for your attention. I am in the process of uploading the 1.7B model files which will be available in the next 1-2 hours.