| library_name: transformers | |
| pipeline_tag: text-classification | |
| base_model: answerdotai/ModernBERT-base | |
| language: | |
| - en | |
| tags: | |
| - text-classification | |
| - memory | |
| - darkmem | |
| - modernbert | |
| # darkmem-classifier-v1 | |
| Seven-class memory-type classifier for darkmem. Labels: fact, decision, preference, problem, reference, architecture, milestone. | |
| ## Metrics | |
| accuracy 0.975 / macro F1 0.975 on 1,000-row gold (`gold_v3.jsonl`). | |
| ## Base model | |
| [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) | |
| ## Usage | |
| ```python | |
| from transformers import AutoModelForSequenceClassification, AutoTokenizer | |
| tok = AutoTokenizer.from_pretrained("darkraise/darkmem-classifier-v1", trust_remote_code=True) | |
| model = AutoModelForSequenceClassification.from_pretrained("darkraise/darkmem-classifier-v1", trust_remote_code=True) | |
| ``` | |
| ## License | |
| Inherits the license of the base model. Fine-tuned weights published under the | |
| same terms unless noted otherwise in the repo. | |
| ## Provenance | |
| Fine-tuned as part of [darkmem](https://github.com/) — a centralized memory | |
| system for AI agents. Training recipe and evaluation scripts are in the | |
| `fine-tuning/` subtree of the darkmem repository. | |