Downloads · 30 days
0
continual-learning-routing
Specialgfhdhdh/continual-learning-routing
continual-learning-routing is a machine learning model from Specialgfhdhdh. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Official implementation of a resource-constrained, sample-efficient continual learning framework utilizing hybrid memory routing and LFM-2.5-350M embeddings.
Access
Public
Updated Oct 5, 2026
Repo size
88.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt12.1 MB · 74%
At a glance
- Access
- Public
- Created
- Sep 18, 2026
- Updated
- Oct 5, 2026
- SHA
- 4a92838d
Model card
From the Hugging Face model README
🧠 Hybrid Episodic Memory & Parametric Routing with LFM-2.5-350M
Official implementation of a resource-constrained, sample-efficient continual learning framework utilizing hybrid memory routing and LFM-2.5-350M embeddings.
🚀 Key Features
- O(1) Streaming Adaptability: Dynamic routing between the parametric prediction head and episodic memory lookup: $$p_t(y) = (1-\alpha) p_{\text{head}}(y) + \alpha p_{\text{mem}}(y)$$
- LFM-2.5-350M Embedded Features: Ultra-efficient representation encoding for downstream low-latency streaming routing.
- Zero-Shot Fictional Knowledge Ingestion: Proven 100.0% immediate recall on completely unseen, dynamically streamed factual injections.
- Optimized Storage Policies: High performance stability down to a capacity of $M=10$ with Balanced Eviction memory schemas.
- Created
- Sep 18, 2026
- Updated
- Oct 5, 2026