Instructions to use 01-ai/Yi-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 01-ai/Yi-9B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="01-ai/Yi-9B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-9B") model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-9B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use 01-ai/Yi-9B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "01-ai/Yi-9B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "01-ai/Yi-9B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/01-ai/Yi-9B
- SGLang
How to use 01-ai/Yi-9B 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 "01-ai/Yi-9B" \ --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": "01-ai/Yi-9B", "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 "01-ai/Yi-9B" \ --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": "01-ai/Yi-9B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use 01-ai/Yi-9B with Docker Model Runner:
docker model run hf.co/01-ai/Yi-9B
Details about expansion
#9
by icoderzqliu - opened
Hello, you mentioned 'After width expansion, there was a significant decline in the model's performance' in the blog, I would like to know some details about the width expansion, is it achieved by expanding the dimensions of the hidden layer? Or what method? Thank you!
Inspiration may be drawn from the insights presented in these two articles https://arxiv.org/abs/2112.11446, https://arxiv.org/abs/2110.07143
itsliupeng changed discussion status to closed