Instructions to use microsoft/phi-1_5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/phi-1_5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="microsoft/phi-1_5")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1_5") model = AutoModelForCausalLM.from_pretrained("microsoft/phi-1_5") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use microsoft/phi-1_5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "microsoft/phi-1_5" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "microsoft/phi-1_5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/microsoft/phi-1_5
- SGLang
How to use microsoft/phi-1_5 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 "microsoft/phi-1_5" \ --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": "microsoft/phi-1_5", "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 "microsoft/phi-1_5" \ --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": "microsoft/phi-1_5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use microsoft/phi-1_5 with Docker Model Runner:
docker model run hf.co/microsoft/phi-1_5
Load model for sentiment analysis or classification
When I load the model for AutoModelForSequenceClassification I get an error:
ValueError: Unrecognized configuration class <class 'transformers_modules.phi-1_5.configuration_mixformer_sequential.MixFormerSequentialConfig'> for this kind of AutoModel: AutoModelForSequenceClassification.
Model type should be one of AlbertConfig, BartConfig, BertConfig, BigBirdConfig, BigBirdPegasusConfig, BioGptConfig, BloomConfig, CamembertConfig, CanineConfig, LlamaConfig, ...
Is it possible to load the model for different tasks than text generation, like semantic analysis or classification tasks?
Hello @ThetaPhiPsi ! I hope everything is going well with you.
It is possible, but you will need to implement a new head to the model. Right now, the only head we have is for Causal LM. However, you should be able to load a pre-trained model for Causal LM, remove the head, and attach a new head to the model, for example, a classification head.
You will also need to fine-tune the model on this new downstream task.
Regards,
Gustavo.
Hello Gustavo,
thank you very much for your reply.
I was a bit overwhelmed by Huggingface's configuration zoo and initially thought that all models offered the same interface, which understandably is not the case.
Thanks for the explanation, I know what to do!
Regards,
Jürgen
Hello @gugarosa
Thank you for the guidance. However, I am still facing challenges in implementing a classification head on the pretrained model. I was wondering if you could provide a more detailed walkthrough or code snippets on how to properly achieve that.
Thanx a lot !