Depth and Scale in the Sub-150M Regime: JugnuLM-53M vs JugnuLM-110M
cs.AI, cs.CL
Submitted: 2026-09-13
Updated: 2026-09-13
Code: https://github.com/AltSlate-Labs/jugnu
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen3 Technical Report
- GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
- RoFormer: Enhanced Transformer with Rotary Position Embedding
- GLU Variants Improve Transformer
- Root Mean Square Layer Normalization
- Query-Key Normalization for Transformers
- PaLM: Scaling Language Modeling with Pathways
- The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
- MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Pointer Sentinel Mixture Models
- Value Residual Learning
- Distilling the Knowledge in a Neural Network
- SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection