Downloads · 30 days
0
synthetic-stroke-temporal-encoder
therayelab/synthetic-stroke-temporal-encoder
synthetic-stroke-temporal-encoder is a feature extraction model from therayelab. Use it when you need embeddings to search or compare text. It is set up for peft. The card lists the license as other.
LoRA adapter for Qwen/Qwen3-Embedding-0.6B, trained on therayelab/synthetic-stroke-patients-v3 using adjacent temporal views of the same synthetic patient as contrastive positives.
Access
Public
Updated Sep 23, 2026
Repo size
48.5 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors55.1 MB · 82%
At a glance
- Task
- Feature Extraction
- Library
- peft
- License
- other
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026
- SHA
- 953fdc7e
Base models
Model card
From the Hugging Face model README
Synthetic Stroke Temporal Patient-State Encoder
LoRA adapter for Qwen/Qwen3-Embedding-0.6B, trained on therayelab/synthetic-stroke-patients-v3 using adjacent temporal
views of the same synthetic patient as contrastive positives.
Intended use
Exploratory representation-learning and agentic-AI research only.
Limitations
This model was trained exclusively on wholly synthetic pilot data. It is not clinically validated and must not be used for patient care or claims of real-world clinical performance.
See run_config.json and the CSV metrics for the complete experimental settings.
- Task
- Feature Extraction
- Library
- peft
- License
- other
- Languages
- en
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026