FL-12B-4 🚧

⚠️ Model in training... This model is currently being fine-tuned. Weights and evaluation results are not final yet.

Status

• Dataset prepared
• Training started
• Training completed
• Evaluation
• Final weights uploaded

Details

• Base model: JetBrains/Mellum2-12B-A2.5B-Base
• Method: QLoRA
• Language: English

Check back soon for updates.