AI & ML interests

Spiking Neural Networks (SNN) for efficient LLM distillation. We build 1B-parameter student models distilled from Llama 3, Qwen 3.6, and CodeLlama using biologically-inspired spike-based activation. Focus: ultra-low latency inference on consumer GPUs (RTX 5070 Ti), neuromorphic computing, and multi-teacher ensemble distillation. Open-source models for code generation and general reasoning.

Organization Card

⚡ VERTEX-1B-SNN

1B Parameter Spiking Neural Network distilled from Llama 3 8B, Qwen 3.6 27B, CodeLlama 7B, and Llama 2 7B.

Built by Mohamed Amine, CEO of VERTEX AI, Morocco.

Model Architecture

Component Specification
Parameters 1B
Architecture Spiking Transformer (SNN)
Hidden Dim 512
Layers 8
Attention Heads 8
Spike Time Steps 12
Vocabulary 128,256 (Llama 3)
Precision BF16

Distillation

  • Hard Loss: Ground-truth next-token prediction
  • Soft Loss: KL divergence from teacher ensemble
  • Consistency: Entropy regularization
  • Router Loss: Task-conditioned specialization (general/code/reasoning)

Teachers

Model Weight Specialization
Llama 3 8B 30% General + Reasoning
Qwen 3.6 27B 25% Code + Agentic
Llama 2 7B 25% General
CodeLlama 7B 20% Pure Code

Hardware

Optimized for NVIDIA RTX 5070 Ti (16GB VRAM) with sequential teacher loading, 4-bit quantization, and LoRA adapters.

Citation

@misc{vertex-1b-snn-2026,
  title={VERTEX-1B-SNN: Efficient Spiking Neural Network Distillation for Consumer GPUs},
  author={Mohamed Amine},
  year={2026},
  organization={VERTEX AI},
  url={https://huggingface.co/vertex-snn}
}

Links

models 0

None public yet

datasets 0

None public yet