🧠 Model

StableBeluga2

by petals-team

--- datasets: - conceptofmind/cot_submix_original - conceptofmind/flan2021_submix_original - conceptofmind/t0_submix_original - conceptofmind/niv2_submix_origin

πŸ• Updated 12/21/2025
Compare This Model

Technical Specifications

Tasktext-generation
πŸ”„ Daily sync (11:00 Beijing)

Based on open-source metadata snapshot. Last synced: Dec 21, 2025

πŸ“Š FNI Methodology πŸ“š Knowledge Baseℹ️ Verify with original source

🧠 Architecture Explorer

Neural network architecture

1 Input Layer
2 Hidden Layers
3 Attention
4 Output Layer

Technical Specifications

Tasktext-generation

Model Card

This repository contains the model from the stabilityai/StableBeluga2 repository with the following changes: 1. Storing weights in instead of . This leads to 2x smaller files and a small quality loss, which is not significant compared to the loss caused by NF4 quantization used in...

πŸ“ Limitations & Considerations

  • β€’ Benchmark scores may vary based on evaluation methodology and hardware configuration.
  • β€’ VRAM requirements are estimates; actual usage depends on quantization and batch size.
  • β€’ FNI scores are relative rankings and may change as new models are added.
  • ⚠ License Unknown: Verify licensing terms before commercial use.
  • β€’ Source: Unknown

πŸ“š Related Resources

πŸ“„ Related Papers

No related papers linked yet. Check the model's official documentation for research papers.

πŸ“Š Training Datasets

Training data information not available. Refer to the original model card for details.

πŸ”— Related Models

Data unavailable

πŸš€ What's Next?