Instructions to use 01-ai/Yi-34B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 01-ai/Yi-34B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="01-ai/Yi-34B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-34B") model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-34B") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use 01-ai/Yi-34B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "01-ai/Yi-34B" # 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-34B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/01-ai/Yi-34B
- SGLang
How to use 01-ai/Yi-34B 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-34B" \ --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-34B", "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-34B" \ --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-34B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use 01-ai/Yi-34B with Docker Model Runner:
docker model run hf.co/01-ai/Yi-34B
will chat model opensource?
#6
by lucasjin - opened
the website it says has 200k context window, but README says not, what exactly length it supports?
Yi-200K base models will be released today.
what exactly length it supports?
The context length supported by both Yi-6B and Yi-34 is just as documented:
Both of them are trained with 4K sequence length and can be extended to 32K during inference time.
the website it says has 200k context window, but README says not
Hold tight! They'll be released sooooon 🤗
thank u! excellent job!
lucasjin changed discussion status to closed
BTW, what about chat model/
This comment has been hidden
Yes, the chat model is estimated to be released in the next several weeks this month.