80 lines
3.9 KiB
Markdown
80 lines
3.9 KiB
Markdown
---
|
|
library_name: transformers
|
|
license: llama3.2
|
|
metrics:
|
|
- accuracy
|
|
- perplexity
|
|
base_model:
|
|
- meta-llama/Llama-3.2-1B
|
|
---
|
|
|
|
# Model Card for oopere/pruned20-llama-1b
|
|
|
|
<!-- Provide a quick summary of what the model is/does. -->
|
|
This model is a pruned version of the Llama-3.2-1b model, with a parameter reduction of 20% in the MLP Layers.
|
|
The pruning process aims to enhance computational efficiency while maintaining acceptable performance across specific tasks.
|
|
This model is not intended to be used directly, but rather to be fine-tuned for specific tasks where it can achieve equal or superior performance compared to fine-tuning the base model for the same task.
|
|
|
|
|
|
## Model Details
|
|
|
|
- **Model Type:** Pruned version of LLaMA-3.2 using structured pruning
|
|
- **Original Model:** meta-llama/Llama-3.2-1B
|
|
- **Pruning Method:** Structured pruning of MLP layers using importance scores based on absolute maximum weights
|
|
- **Size Reduction:** 13.7% (from 1.24B to 1.07B parameters)
|
|
- **Architecture:** Same as original LLaMA but with reduced MLP layer sizes
|
|
- **Language(s):** Same as original model
|
|
- **License:** Same as original model
|
|
- **Developed by:** [Pere Martra](https://huggingface.co/oopere)
|
|
|
|
These models are part of the study "[Exploring GLU Expansion Ratios: Structured Pruning in Llama-3.2 Models](https://doi.org/10.31219/osf.io/qgxea)". They explore structured pruning in GLU-based architectures using Llama-3.2 (1B and 3B variants). The pruning experiments target optimal expansion ratios to balance performance, computational efficiency, and environmental sustainability. The models were evaluated across multiple benchmarks, including BoolQ, ARC-Easy, and MUSR, and demonstrate significant efficiency gains while maintaining robust task performance.
|
|
|
|
### Performance on Standard Benchmarks
|
|
|
|
| Benchmark | Original Model | Pruned Model | Relative Change |
|
|
| ---- | ---- | ---- | ---- |
|
|
| ARC-Easy | 65.19% | 53.03% | -18.7% |
|
|
| BoolQ | 64.16% | 62.32% | -2.9% |
|
|
| LAMBADA-OpenAI | 62.20% | 42.13% | -32.3% |
|
|
| LAMBADA-Standard | 53.46% | 41.04% | -23.2% |
|
|
|
|
### Key Findings
|
|
- Maintains strong performance on binary classification tasks (BoolQ)
|
|
- Moderate degradation on reasoning tasks (ARC-Easy)
|
|
- Significant impact on long-range comprehension (LAMBADA)
|
|
|
|
### Limitations
|
|
- Reduced performance on tasks requiring complex language understanding
|
|
- More significant degradation on tasks requiring long-range dependencies
|
|
- May not be suitable for applications requiring high accuracy on language completion tasks
|
|
|
|
### Implementation Details
|
|
- **Pruning Notebook:** [Detailed implementation and methodology](https://github.com/peremartra/Large-Language-Model-Notebooks-Course/blob/main/6-PRUNING/6_3_pruning_structured_llama3.2-1b_OK.ipynb)
|
|
- **GitHub Repository:** [LLM Course](https://github.com/peremartra/Large-Language-Model-Notebooks-Course)
|
|
|
|
### Pruning Method
|
|
- **Technique:** Structured pruning targeting MLP layers
|
|
- **Pruning Ratio:** 20% of neurons removed from MLP layers
|
|
- **Selection Criteria:** Importance scoring based on absolute maximum weights
|
|
- **Architecture Specifics:** Maintained GLU structure during pruning
|
|
|
|
### Hardware Requirements
|
|
- Reduced memory footprint compared to original model
|
|
- Can run on hardware with ~20% less memory than original
|
|
|
|
## Acknowledgments
|
|
- Thanks to [Mariusz Kurman](https://huggingface.co/mkurman) for creating [llama-pruning](https://github.com/MedITSolutionsKurman/llama-pruning), a library that extends and improve this pruning methodology.
|
|
|
|
- This model was created following the pruning method described in the paper: The Width Pruning Dichotomy in Llama-3.2
|
|
|
|
```
|
|
@misc{martra2025fragileknowledgerobustinstructionfollowing,
|
|
title={Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2},
|
|
author={Pere Martra},
|
|
year={2025},
|
|
eprint={2512.22671},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CL},
|
|
url={https://arxiv.org/abs/2512.22671},
|
|
}
|
|
``` |