Downloads · 30 days
0
ra225/Llama-2-7b-best_ratio80_rmsnorm_finetuned
Llama-2-7b-best_ratio80_rmsnorm_finetuned is a machine learning model from ra225. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama2.
This model is a pruned and finetuned version of meta-llama/Llama-2-7b-hf, retaining approximately 80% of parameters while maintaining strong performance through genetic algorithm pruning and RMSNorm fine-tuning.
Downloads · 30 days
0
Access
Public
Updated Jan 22, 2026
Repo size
13.5 GB
Likes
0
Public
Click a slice to open those files.
.pt13.5 GB · 100%
From the Hugging Face model README
This model is a pruned and finetuned version of meta-llama/Llama-2-7b-hf, retaining approximately 80% of parameters while maintaining strong performance through genetic algorithm pruning and RMSNorm fine-tuning.
| Metric | Value |
|---|---|
| PPL (Before Fine-tuning) | 8.57 |
| PPL (After Fine-tuning) | 6.71 |
| Improvement | 21.67% |
| Model | PPL (After FT) |
|---|---|
| 50% params | 13.84 |
| 70% params | 8.25 |
| 80% params | 6.71 |
| 90% params | 5.62 |
Llama 2 Community License (inherited from base model)