Model Card for Morbid.AI v0.0.2
Model Details
- Model type: Fine-tuned Llama-2-7b
- Language: English
- License: Apache 2.0
- Fine-tuned from: meta-llama/Llama-2-7b-hf
- Training data: Actuarial-specific mortality dataset with 395 examples
Training Procedure
- Training regime: fp16 mixed precision
- Epochs: 3
- Batch size: 4
- Learning rate: 2e-5
- Hardware: CPU-optimized
Evaluation Results
- Validation accuracy: 87%
- Specialized for mortality and actuarial predictions