Update README.md
Browse files
README.md
CHANGED
@@ -1,20 +1,24 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
3 |
---
|
4 |
This repository hosts both the standard and quantized versions of the Zephyr 7B model, allowing users to choose the version that best fits their resource constraints and performance needs.
|
5 |
|
6 |
# Model Details
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
|
13 |
# Performance and Efficiency
|
14 |
The quantized version of Zephyr 7B is optimized for environments with limited computational resources. It offers:
|
15 |
|
16 |
-
|
17 |
-
|
18 |
|
19 |
# Fine-Tuning
|
20 |
You can fine-tune the Zephyr 7B model on your own dataset to better suit specific tasks or domains. Refer to the Huggingface documentation for guidance on how to fine-tune transformer models.
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
library_name: transformers
|
6 |
+
pipeline_tag: text-generation
|
7 |
---
|
8 |
This repository hosts both the standard and quantized versions of the Zephyr 7B model, allowing users to choose the version that best fits their resource constraints and performance needs.
|
9 |
|
10 |
# Model Details
|
11 |
+
### Model Name: Zephyr 7B
|
12 |
+
### Model Size: 7 billion parameters
|
13 |
+
### Architecture: Transformer-based
|
14 |
+
### Languages: Primarily English, with support for multilingual text
|
15 |
+
### Quantized Version: Available for reduced memory footprint and faster inference
|
16 |
|
17 |
# Performance and Efficiency
|
18 |
The quantized version of Zephyr 7B is optimized for environments with limited computational resources. It offers:
|
19 |
|
20 |
+
### Reduced Memory Usage: The model size is significantly smaller, making it suitable for deployment on devices with limited RAM.
|
21 |
+
### Faster Inference: Quantized models can perform faster inference, providing quicker responses in real-time applications.
|
22 |
|
23 |
# Fine-Tuning
|
24 |
You can fine-tune the Zephyr 7B model on your own dataset to better suit specific tasks or domains. Refer to the Huggingface documentation for guidance on how to fine-tune transformer models.
|