| language: en | |
| license: mit # Adjust based on original model | |
| tags: | |
| - pruning | |
| - sparse | |
| - atropos | |
| - code-generation | |
| # gpt2-xl-structured_pruning | |
| This is a pruned version of [gpt2-xl](https://huggingface.co/gpt2-xl) | |
| generated as part of the Atropos pruning exercise. | |
| ## Pruning Details | |
| - **Strategy:** structured_pruning | |
| - **Method:** PyTorch magnitude-based unstructured pruning | |
| - **Generated by:** Atropos pruning exercise scripts | |
| ## Usage | |
| ```python | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| model = AutoModelForCausalLM.from_pretrained("gpt2-xl-structured_pruning") | |
| tokenizer = AutoTokenizer.from_pretrained("gpt2-xl-structured_pruning") | |
| ``` | |
| ## About Atropos | |
| [Atropos](https://github.com/its-not-rocket-science/atropos) estimates ROI | |
| for pruning and quantization optimizations in LLM deployments. | |
| This model was pruned to validate Atropos projections against actual results. | |
| ## Citation | |
| If you use this model, please cite the original model and Atropos: | |
| ```bibtex | |
| @software{atropos, | |
| title = {Atropos: ROI Estimation for LLM Pruning}, | |
| year = {2026}, | |
| } | |
| ``` | |