Text Generation
Transformers
Safetensors
interpgpt
interpretability
mechanistic-interpretability
task-decomposition
small-language-model
transformer-lens
custom_code
Instructions to use connaaa/interpgpt-standard-23M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use connaaa/interpgpt-standard-23M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="connaaa/interpgpt-standard-23M", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("connaaa/interpgpt-standard-23M", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use connaaa/interpgpt-standard-23M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "connaaa/interpgpt-standard-23M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "connaaa/interpgpt-standard-23M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/connaaa/interpgpt-standard-23M
- SGLang
How to use connaaa/interpgpt-standard-23M 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 "connaaa/interpgpt-standard-23M" \ --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": "connaaa/interpgpt-standard-23M", "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 "connaaa/interpgpt-standard-23M" \ --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": "connaaa/interpgpt-standard-23M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use connaaa/interpgpt-standard-23M with Docker Model Runner:
docker model run hf.co/connaaa/interpgpt-standard-23M
| """ | |
| HuggingFace PretrainedConfig for InterpGPT / TaskGPT. | |
| Mirrors gpt_model.GPTConfig but subclasses transformers.PretrainedConfig | |
| so `AutoConfig` / `AutoModel.from_pretrained(..., trust_remote_code=True)` work. | |
| """ | |
| from transformers import PretrainedConfig | |
| class InterpGPTConfig(PretrainedConfig): | |
| model_type = "interpgpt" | |
| def __init__( | |
| self, | |
| vocab_size: int = 8192, | |
| max_seq_len: int = 512, | |
| n_layers: int = 6, | |
| n_heads: int = 8, | |
| d_model: int = 512, | |
| d_ff: int = 2048, | |
| dropout: float = 0.1, | |
| pad_id: int = 0, | |
| bias: bool = False, | |
| variant: str = "standard", | |
| **kwargs, | |
| ): | |
| self.vocab_size = vocab_size | |
| self.max_seq_len = max_seq_len | |
| self.n_layers = n_layers | |
| self.n_heads = n_heads | |
| self.d_model = d_model | |
| self.d_ff = d_ff | |
| self.dropout = dropout | |
| self.pad_id = pad_id | |
| self.bias = bias | |
| self.variant = variant | |
| kwargs.pop("pad_token_id", None) | |
| super().__init__(pad_token_id=pad_id, **kwargs) | |