Downloads · 30 days
3
5% of all-time downloads
gpt2-torchao-int8_weight_only
medmekk/gpt2-torchao-int8_weight_only
gpt2-torchao-int8_weight_only is a machine learning model from medmekk. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model is a quantized version of the original model gpt2. It has been quantized using int8weightonly quantization with torchao.
All-time downloads
62
Public
Repo size
498 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin249 MB · 100%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Oct 8, 2024
- Updated
- Oct 8, 2024
- SHA
- 0164fab9
Base models
Model card
From the Hugging Face model README
gpt2 (Quantized)
Description
This model is a quantized version of the original model gpt2. It has been quantized using int8_weight_only quantization with torchao.
Quantization Details
- Quantization Type: int8_weight_only
- Group Size: None
Usage
You can use this model in your applications by loading it directly from the Hugging Face Hub:
from transformers import AutoModel
model = AutoModel.from_pretrained("gpt2")
- Type
- gpt2
- Created
- Oct 8, 2024
- Updated
- Oct 8, 2024