Downloads · 30 days
5
19% of all-time downloads
Qwen2.5-72B-Instruct-bnb-4bit
lierseleow/Qwen2.5-72B-Instruct-bnb-4bit
Qwen2.5-72B-Instruct-bnb-4bit is a machine learning model from lierseleow. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
This repository contains quantized weights for Qwen/Qwen2.5-72B-Instruct.
All-time downloads
27
Public
Parameters
72.7B
41.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors41.2 GB · 100%
Parameter types
How the weights are stored.
U870.2B · 97%
Base models
Model card
From the Hugging Face model README
lierseleow/Qwen2.5-72B-Instruct-bnb-4bit (Quantized)
This repository contains quantized weights for Qwen/Qwen2.5-72B-Instruct.
License & Attribution
Built with Alibaba Cloud Qwen 2.5.
This model is a derivative work of Alibaba Clouds's Qwen 2.5 and is governed by the Qwen License Agreement and the Qwen Usage Policy.
- Official License: Qwen License Agreement
- Usage Policy: Qwen Usage Policy
By downloading, copying, or using these quantized weights, you agree to compliance with the terms, conditions, and restrictions outlined.
Quantization Details
- Quantization Method: bitsandbytes
- Bits/Precision: 4bit
- Base Model: Qwen/Qwen2.5-72B-Instruct
Dependencies Details
- transformers version: 5.14.1
- bitsandbytes version: 0.50.0
- Type
- qwen2
- License
- other
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026