Instructions to use nlpzhaof/aligngpt-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nlpzhaof/aligngpt-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nlpzhaof/aligngpt-7b")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("nlpzhaof/aligngpt-7b", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use nlpzhaof/aligngpt-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nlpzhaof/aligngpt-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nlpzhaof/aligngpt-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nlpzhaof/aligngpt-7b
- SGLang
How to use nlpzhaof/aligngpt-7b 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 "nlpzhaof/aligngpt-7b" \ --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": "nlpzhaof/aligngpt-7b", "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 "nlpzhaof/aligngpt-7b" \ --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": "nlpzhaof/aligngpt-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nlpzhaof/aligngpt-7b with Docker Model Runner:
docker model run hf.co/nlpzhaof/aligngpt-7b
Demo on Hub & GPU grant
#2
by merve - opened
Hello πββοΈ congratulations on release!
Would you like to host your demo on Spaces? We can provide Zero GPU (A100 for inference for free) and increase visibility of your model
Yes, we would like to. That sounds fantastic!
@nlpzhaof thanks a lot!
I invited you to our ZeroGPU org, you need to accept the invitation to get access to ZeroGPUs. You can check out the org page for more info.
When building the Space, select the GPU type as zero and simply do:
+import spaces
your_pytorch_model.to('cuda')
+@spaces.GPU
def infer(image, prompt):
return your_pytorch_model(**inputs)
gr.Interface(
fn=infer,
inputs=[gr.Image(), gr.Text()],
outputs=gr.Textbox(),
).launch()