Instructions to use TheBloke/wizardLM-7B-HF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TheBloke/wizardLM-7B-HF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TheBloke/wizardLM-7B-HF")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TheBloke/wizardLM-7B-HF") model = AutoModelForCausalLM.from_pretrained("TheBloke/wizardLM-7B-HF") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use TheBloke/wizardLM-7B-HF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TheBloke/wizardLM-7B-HF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheBloke/wizardLM-7B-HF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TheBloke/wizardLM-7B-HF
- SGLang
How to use TheBloke/wizardLM-7B-HF 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 "TheBloke/wizardLM-7B-HF" \ --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": "TheBloke/wizardLM-7B-HF", "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 "TheBloke/wizardLM-7B-HF" \ --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": "TheBloke/wizardLM-7B-HF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TheBloke/wizardLM-7B-HF with Docker Model Runner:
docker model run hf.co/TheBloke/wizardLM-7B-HF
Save the model as pkl or pt
#5
by adityakad - opened
Hi Tom, I want to deploy the model as AWS SageMaker Endpoint but I don't want to use the model from the Hugging Face Hub.
I get an error when I try to save the model as a pkl file or a pt file. Is there a way to do that?
adityakad changed discussion title from Save the model file to Save the model as pkl or pt
I've never used AWS SageMaker. But the model is already in Pickle .bin format, so are you sure you need to convert it?
Yes, the way AWS SageMaker works in my company, it only accepts models in .pkl or .pt or .th formats. Would that be possible?