Text Generation
Transformers
PyTorch
English
taonet_mini_t2
taonet
taotern
ssm
state-space-model
dplr
custom_code
experimental
Instructions to use TaoTern/TaoNet-mini-T2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TaoTern/TaoNet-mini-T2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TaoTern/TaoNet-mini-T2", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("TaoTern/TaoNet-mini-T2", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TaoTern/TaoNet-mini-T2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TaoTern/TaoNet-mini-T2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TaoTern/TaoNet-mini-T2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TaoTern/TaoNet-mini-T2
- SGLang
How to use TaoTern/TaoNet-mini-T2 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 "TaoTern/TaoNet-mini-T2" \ --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": "TaoTern/TaoNet-mini-T2", "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 "TaoTern/TaoNet-mini-T2" \ --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": "TaoTern/TaoNet-mini-T2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TaoTern/TaoNet-mini-T2 with Docker Model Runner:
docker model run hf.co/TaoTern/TaoNet-mini-T2
| """Model architecture registry and factory.""" | |
| from typing import Dict, Type, Optional | |
| import torch | |
| from taoTrain.core import BaseModel | |
| from taoTrain.config import ModelConfig | |
| # Global registry for model architectures | |
| _ARCHITECTURE_REGISTRY: Dict[str, Type[BaseModel]] = {} | |
| def register_architecture(name: str): | |
| """Decorator to register a custom model architecture.""" | |
| def decorator(cls: Type[BaseModel]): | |
| if name in _ARCHITECTURE_REGISTRY: | |
| raise ValueError(f"Architecture '{name}' is already registered") | |
| _ARCHITECTURE_REGISTRY[name] = cls | |
| return cls | |
| return decorator | |
| def get_registered_architectures() -> Dict[str, Type[BaseModel]]: | |
| """Get all registered architectures.""" | |
| return _ARCHITECTURE_REGISTRY.copy() | |
| def get_model( | |
| config: ModelConfig, | |
| device: Optional[torch.device] = None, | |
| ) -> BaseModel: | |
| """ | |
| Create a model instance from config. | |
| Args: | |
| config: ModelConfig instance | |
| device: Device to create model on (defaults to CPU) | |
| Returns: | |
| Model instance | |
| """ | |
| if device is None: | |
| device = torch.device('cpu') | |
| # Handle both enum and string values | |
| arch_type = config.architecture_type | |
| if isinstance(arch_type, str): | |
| arch_name = arch_type | |
| else: | |
| arch_name = arch_type.value | |
| if arch_name not in _ARCHITECTURE_REGISTRY: | |
| raise ValueError( | |
| f"Unknown architecture: {arch_name}. " | |
| f"Available: {list(_ARCHITECTURE_REGISTRY.keys())}" | |
| ) | |
| model_class = _ARCHITECTURE_REGISTRY[arch_name] | |
| model = model_class(config).to(device) | |
| return model | |
| def register_builtin_architectures(): | |
| """Register all built-in architectures.""" | |
| # Import here to register (avoid circular imports) | |
| from . import transformer # noqa: F401 | |
| from . import taonet # noqa: F401 | |
| from . import taonet_ssm # noqa: F401 | |
| # Auto-register built-in architectures when module is imported | |
| register_builtin_architectures() | |