Downloads · 30 days
8
14% of all-time downloads
darkmem-classifier-v1
darkraise/darkmem-classifier-v1
darkmem-classifier-v1 is a text classification model from darkraise. Use it when you need a label for a piece of text. It is set up for transformers.
Seven-class memory-type classifier for darkmem. Labels: fact, decision, preference, problem, reference, architecture, milestone.
All-time downloads
58
Public
Parameters
150M
598 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors598 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- modernbert
- Access
- Public
- Created
- Apr 17, 2026
- Updated
- Apr 19, 2026
- SHA
- 838c09ea
Try a prompt
Base models
Model card
From the Hugging Face model README
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
Usage
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 — a centralized memory
system for AI agents. Training recipe and evaluation scripts are in the
fine-tuning/ subtree of the darkmem repository.
- Task
- Text Classification
- Library
- transformers
- Type
- modernbert
- Languages
- en
- Created
- Apr 17, 2026
- Updated
- Apr 19, 2026