Feature Extraction
Transformers
Safetensors
English
system_one
multi-task-classification
synthetic-data
research
custom-code
custom_code
Instructions to use DavidHatley/system-one-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DavidHatley/system-one-mini with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="DavidHatley/system-one-mini", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DavidHatley/system-one-mini", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from DavidHatley/system-one-mini: direct link, hf CLI and curl.
- Browser
- Download file 2.45 kB
-
https://huggingface.co/DavidHatley/system-one-mini/resolve/main/config.json
- Command line
-
hf download hf://DavidHatley/system-one-mini/config.json
-
curl -L -o config.json https://huggingface.co/DavidHatley/system-one-mini/resolve/main/config.json
2.45 kB
| { | |
| "architectures": [ | |
| "SystemOneModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "modeling_system_one.SystemOneConfig", | |
| "AutoModel": "modeling_system_one.SystemOneModel" | |
| }, | |
| "calibration": { | |
| "log_temperature_bounds": [ | |
| -3.0, | |
| 3.0 | |
| ], | |
| "method": "per_head_temperature_scaling", | |
| "objective": "mean_nll", | |
| "sha256": "2ebc5e113626a8de829fe2d1b1303f05ff56dc6a85cbc0facefea445f6a9a63d", | |
| "split": "calibration" | |
| }, | |
| "decisions": [ | |
| { | |
| "name": "task_complete", | |
| "options": [ | |
| "false", | |
| "true" | |
| ], | |
| "prompt": "Has the task been successfully completed?" | |
| }, | |
| { | |
| "name": "should_retry", | |
| "options": [ | |
| "false", | |
| "true" | |
| ], | |
| "prompt": "Should the same failed action be retried without changing it?" | |
| }, | |
| { | |
| "name": "failure_source", | |
| "options": [ | |
| "code", | |
| "environment", | |
| "test", | |
| "dependency", | |
| "unknown" | |
| ], | |
| "prompt": "What is the source of the original reproduced failure?" | |
| }, | |
| { | |
| "name": "next_action", | |
| "options": [ | |
| "inspect_code", | |
| "rerun_tests", | |
| "inspect_environment", | |
| "revert_change", | |
| "escalate" | |
| ], | |
| "prompt": "What action should the agent take next under the diagnostic policy?" | |
| }, | |
| { | |
| "name": "evidence_sufficient", | |
| "options": [ | |
| "false", | |
| "true" | |
| ], | |
| "prompt": "Does exactly one controlled intervention identify the original failure source?" | |
| } | |
| ], | |
| "encoder_config": { | |
| "activation": "gelu", | |
| "attention_dropout": 0.1, | |
| "attn_implementation": null, | |
| "dim": 768, | |
| "dropout": 0.1, | |
| "hidden_dim": 3072, | |
| "initializer_range": 0.02, | |
| "max_position_embeddings": 512, | |
| "model_type": "distilbert", | |
| "n_heads": 12, | |
| "n_layers": 6, | |
| "pad_token_id": 0, | |
| "qa_dropout": 0.1, | |
| "seq_classif_dropout": 0.2, | |
| "sinusoidal_pos_embds": false, | |
| "tie_weights_": true, | |
| "vocab_size": 30522 | |
| }, | |
| "head_depth": 2, | |
| "head_dropout": 0.1, | |
| "max_length": 256, | |
| "model_type": "system_one", | |
| "num_labels_per_head": [ | |
| 2, | |
| 2, | |
| 5, | |
| 5, | |
| 2 | |
| ], | |
| "representation_dropout": 0.1, | |
| "temperatures": [ | |
| 3.257378625530402, | |
| 7.389464733023116, | |
| 20.085460565518172, | |
| 3.731100212778321, | |
| 20.085425529109152 | |
| ], | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.53.3" | |
| } | |