Downloads · 30 days
7
15% of all-time downloads
Mistral-7B-v0.1-4bit-8rank
smallsuper/Mistral-7B-v0.1-4bit-8rank
Mistral-7B-v0.1-4bit-8rank is a feature extraction model from smallsuper. Use it when you need embeddings to search or compare text. It is set up for transformers.
This is a bare model without any output layer or classification head. It has been quantized to be used for feature extraction tasks.
All-time downloads
46
Public
Parameters
7.1B
14.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.3 GB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- mistral
- Access
- Public
- Created
- Apr 29, 2024
- Updated
- May 6, 2024
- SHA
- d8b76298
Model card
From the Hugging Face model README
Overview
This is a bare model without any output layer or classification head. It has been quantized to be used for feature extraction tasks.
Usage
This model is intended to be used as a base for training on downstream tasks. In order to use it for predictions and inference, it should be fine-tuned on a specific task with an appropriate output layer or classification head added.
Quantization
The model has been quantized using the following parameters:
Lora alpha: 16
Lora rank: 8
Lora target modules: all-linear
bits: 4
LoftQ iterations: 5
- Task
- Feature Extraction
- Library
- transformers
- Type
- mistral
- Created
- Apr 29, 2024
- Updated
- May 6, 2024