Instructions to use RunsenXu/PointLLM_7B_v1.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RunsenXu/PointLLM_7B_v1.2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RunsenXu/PointLLM_7B_v1.2")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("RunsenXu/PointLLM_7B_v1.2", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use RunsenXu/PointLLM_7B_v1.2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RunsenXu/PointLLM_7B_v1.2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RunsenXu/PointLLM_7B_v1.2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/RunsenXu/PointLLM_7B_v1.2
- SGLang
How to use RunsenXu/PointLLM_7B_v1.2 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 "RunsenXu/PointLLM_7B_v1.2" \ --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": "RunsenXu/PointLLM_7B_v1.2", "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 "RunsenXu/PointLLM_7B_v1.2" \ --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": "RunsenXu/PointLLM_7B_v1.2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use RunsenXu/PointLLM_7B_v1.2 with Docker Model Runner:
docker model run hf.co/RunsenXu/PointLLM_7B_v1.2
Can not load model
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("RunsenXu/PointLLM_7B_v1.1")
ValueError: The checkpoint you are trying to load has model type pointllm but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
Please help me solve this issues
Hi, PointLLM is not officially supported by the Transformers library. Please check our GitHub repo for instructions: https://github.com/OpenRobotLab/PointLLM/tree/master