Instructions to use 01-ai/Yi-1.5-34B-32K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 01-ai/Yi-1.5-34B-32K with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="01-ai/Yi-1.5-34B-32K")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-1.5-34B-32K") model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-1.5-34B-32K", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use 01-ai/Yi-1.5-34B-32K with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "01-ai/Yi-1.5-34B-32K" # 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-1.5-34B-32K", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/01-ai/Yi-1.5-34B-32K
- SGLang
How to use 01-ai/Yi-1.5-34B-32K 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-1.5-34B-32K" \ --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-1.5-34B-32K", "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-1.5-34B-32K" \ --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-1.5-34B-32K", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use 01-ai/Yi-1.5-34B-32K with Docker Model Runner:
docker model run hf.co/01-ai/Yi-1.5-34B-32K
what is the difference between this model and 01-ai/Yi-1.5-34B?
what is the difference between this model and 01-ai/Yi-1.5-34B?
This is a base model with 32K context length, good for community finetunes
Our previously released 01-ai/Yi-1.5-34B has a native context length of 4k.
This is a base model with 32K context length, good for community finetunes
Our previously released 01-ai/Yi-1.5-34B has a native context length of 4k.
Thank you very much for the longer context model.
Is there any plan to show more information related to the difference between 4k, 16k, 32k and also chat/base different?
Maybe it is somewhere posted?
This is a base model with 32K context length, good for community finetunes
Our previously released 01-ai/Yi-1.5-34B has a native context length of 4k.Thank you very much for the longer context model.
Is there any plan to show more information related to the difference between 4k, 16k, 32k and also chat/base different?
Maybe it is somewhere posted?
I'll try my best to explain these in a tech blog.
If you are uncertain which version to use, your first choice might probably be 4k chat version.