Downloads · 30 days
8
32% of all-time downloads
Aarushhh_-_untrained-Qwen-2.5-7b-Instruct-Pruned-8bits
RichardErkhov/Aarushhh_-_untrained-Qwen-2.5-7b-Instruct-Pruned-8bits
Aarushhh_-_untrained-Qwen-2.5-7b-Instruct-Pruned-8bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
25
Public
Parameters
4.4B
5.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.4 GB · 100%
Parameter types
How the weights are stored.
I83.3B · 75%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
untrained-Qwen-2.5-7b-Instruct-Pruned - bnb 8bits
- Model creator: https://huggingface.co/Aarushhh/
- Original model: https://huggingface.co/Aarushhh/untrained-Qwen-2.5-7b-Instruct-Pruned/
Original model description:
library_name: transformers tags: []
A pruned version of Qwen 2.5 7B instruct
it has 14 layers (vs the usual 24)
the model is not trained yet
- Type
- qwen2
- Created
- Mar 14, 2025
- Updated
- Mar 14, 2025