You can deploy this model and start earning money today!

Nabeelah04/
quantized_models

Name: quantized_models
Availability: InStock

Views

No views yet

GPT-2 Quantized Models

Project Overview

This repository contains the model weights for the quantized models used in the proje

Models Included

This repository contains several variants of GPT-2 pruned at different sparsity levels (30%, 50%, 70%):

Base Model: The original, GPT-2 model used as a baseline.
FP-16: Floating point 16 Model.
INT-8: The quantized INT-8 model.

How to Load a Model

You can load any of these specific models directly using the transformers library:

python

from transformers import GPT2LMHeadModel, GPT2Tokenizer

# Example: Loading the 30% sparsity magnitude attention head model
model_id = "Nabeelah04/quantized_models/gpt2_fp16_gpu"