Text Generation
Transformers
Safetensors
interpgpt
interpretability
mechanistic-interpretability
task-decomposition
small-language-model
transformer-lens
custom_code
Instructions to use connaaa/interpgpt-adhd-23M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use connaaa/interpgpt-adhd-23M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="connaaa/interpgpt-adhd-23M", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("connaaa/interpgpt-adhd-23M", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use connaaa/interpgpt-adhd-23M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "connaaa/interpgpt-adhd-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-adhd-23M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/connaaa/interpgpt-adhd-23M
- SGLang
How to use connaaa/interpgpt-adhd-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-adhd-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-adhd-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-adhd-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-adhd-23M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use connaaa/interpgpt-adhd-23M with Docker Model Runner:
docker model run hf.co/connaaa/interpgpt-adhd-23M
| { | |
| "vocab_size": 8197, | |
| "max_seq_len": 512, | |
| "n_layers": 6, | |
| "n_heads": 8, | |
| "d_model": 512, | |
| "d_ff": 2048, | |
| "dropout": 0.25, | |
| "pad_id": 8196, | |
| "bias": false, | |
| "variant": "adhd", | |
| "transformers_version": "5.5.4", | |
| "architectures": null, | |
| "output_hidden_states": false, | |
| "return_dict": true, | |
| "dtype": null, | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "problem_type": null, | |
| "_name_or_path": "", | |
| "pad_token_id": 8196, | |
| "auto_map": { | |
| "AutoConfig": "configuration_interpgpt.InterpGPTConfig", | |
| "AutoModel": "modeling_interpgpt.InterpGPTModel" | |
| }, | |
| "model_type": "interpgpt", | |
| "output_attentions": false | |
| } |