Downloads · 30 days
11
42% of all-time downloads
Llama-3.1-8B-bnb-4bit
medmekk/Llama-3.1-8B-bnb-4bit
Llama-3.1-8B-bnb-4bit 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 medmekk/Llama-3.1-8B-bnb-4bit. It has been quantized using int4 quantization with bitsandbytes.
All-time downloads
26
Public
Parameters
7.7B
4.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.7 GB · 100%
Parameter types
How the weights are stored.
U87.2B · 93%
Model card
From the Hugging Face model README
medmekk/Llama-3.1-8B-bnb-4bit (Quantized)
Description
This model is a quantized version of the original model medmekk/Llama-3.1-8B-bnb-4bit. It has been quantized using int4 quantization with bitsandbytes.
Quantization Details
- Quantization Type: int4
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
- bnb_4bit_quant_storage: uint8
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("medmekk/Llama-3.1-8B-bnb-4bit")
- Type
- llama
- Created
- Mar 17, 2025
- Updated
- Mar 17, 2025