Downloads · 30 days
3
3% of all-time downloads
medmekk/Meta-Llama-3-8B-torchao-int8_dynamic_activation_int8_weight
Meta-Llama-3-8B-torchao-int8_dynamic_activation_int8_weight 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.
--- basemodel: - meta-llama/Meta-Llama-3-8B ---
Downloads · 30 days
3
3% of all-time downloads
All-time downloads
91
Public
Repo size
9.1 GB
Likes
0
Public
Click a slice to open those files.
.bin9.1 GB · 100%
From the Hugging Face model README
base_model:
- meta-llama/Meta-Llama-3-8B
---
# meta-llama/Meta-Llama-3-8B (Quantized)
## Description
This model is a quantized version of the original model `meta-llama/Meta-Llama-3-8B`. It has been quantized using int8_dynamic_activation_int8_weight quantization with torchao.
## Quantization Details
- **Quantization Type**: int8_dynamic_activation_int8_weight
- **Group Size**: None
## Usage
You can use this model in your applications by loading it directly from the Hugging Face Hub:
```python
from transformers import AutoModel
model = AutoModel.from_pretrained("meta-llama/Meta-Llama-3-8B")