Downloads · 30 days
12
29% of all-time downloads
Spiking-CODER-V1
AmanC007/Spiking-CODER-V1
Spiking-CODER-V1 is a text generation model from AmanC007. Use it when you need the model to write or continue text. It is set up for transformers.
Spiking-CODER v1 is a fine-tuned LLM specialized for Spiking Neural Network (SNN) programming tasks. It was trained using the Phase A and Phase B datasets.
All-time downloads
42
Public
Parameters
3.2B
19.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt12.9 GB · 67%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Aug 26, 2025
- Updated
- Aug 26, 2025
- SHA
- 4f3f8bb0
Try a prompt
Base models
Model card
From the Hugging Face model README
Spiking-CODER v1 🧠⚡
Spiking-CODER v1 is a fine-tuned LLM specialized for Spiking Neural Network (SNN) programming tasks.
It was trained using the Phase A and Phase B datasets.
📊 Training Data
- Phase A - v1: 50K raw SNN code samples from GitHub.
- Phase B - v1: 100K synthetic prompt–output pairs generated by DeepSeek-Coder-6.7B-Instruct and Llama-3.1-8B-Instruct.
🎯 Key Features
- Optimized for function, class, and import completions in SNN codebases.
- Balances authentic raw code grounding with synthetic instruction-style augmentation.
- Strong performance on SNNBench evaluation across frameworks and categories.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Languages
- en
- Created
- Aug 26, 2025
- Updated
- Aug 26, 2025