Instructions to use Jiabin99/HiGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jiabin99/HiGPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Jiabin99/HiGPT")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Jiabin99/HiGPT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Jiabin99/HiGPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jiabin99/HiGPT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jiabin99/HiGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Jiabin99/HiGPT
- SGLang
How to use Jiabin99/HiGPT 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 "Jiabin99/HiGPT" \ --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": "Jiabin99/HiGPT", "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 "Jiabin99/HiGPT" \ --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": "Jiabin99/HiGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Jiabin99/HiGPT with Docker Model Runner:
docker model run hf.co/Jiabin99/HiGPT
I cannot import the model through Huggingface
I use the transformers version 4.45.0.dev0. After I use the code model = AutoModelForCausalLM.from_pretrained('Jiabin99/HiGPT'). It shows the error:Traceback (most recent call last):
File "", line 1, in
File "E:\Software\Anaconda\install\envs\py312\Lib\site-packages\transformers\models\auto\auto_factory.py", line 520, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Software\Anaconda\install\envs\py312\Lib\site-packages\transformers\models\auto\configuration_auto.py", line 1016, in from_pretrained
raise ValueError(
ValueError: The checkpoint you are trying to load has model type HeteroLlama 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.
model = AutoModelForCausalLM.from_pretrained("E:\Study\GNN\Code\HeteroBackdoorAttack\LLM\HiGPT")
:1: SyntaxWarning: invalid escape sequence '\S'
Traceback (most recent call last):
File "E:\Software\Anaconda\install\envs\py312\Lib\site-packages\transformers\models\auto\configuration_auto.py", line 1014, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Software\Anaconda\install\envs\py312\Lib\site-packages\transformers\models\auto\configuration_auto.py", line 716, in getitem
raise KeyError(key)
KeyError: 'HeteroLlama'
How to address that?