Commit
•
ee38300
1
Parent(s):
ad4bd3a
Update README.md
Browse files
README.md
CHANGED
|
@@ -32,6 +32,10 @@ To accommodate different hardware configurations and performance needs, Nidum-Li
|
|
| 32 |
| **Nidum-Limitless-Gemma-2B-Q8_0.gguf** | Provides higher precision with increased memory usage, suitable for tasks requiring more accuracy. |
|
| 33 |
| **Nidum-Limitless-Gemma-2B-F16.gguf** | Full 16-bit floating point precision for maximum accuracy, ideal for high-end GPUs. |
|
| 34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
## How to Use:
|
| 36 |
|
| 37 |
To get started with Nidum-Limitless-Gemma-2B-GGUF, you can use the following sample code for testing:
|
|
|
|
| 32 |
| **Nidum-Limitless-Gemma-2B-Q8_0.gguf** | Provides higher precision with increased memory usage, suitable for tasks requiring more accuracy. |
|
| 33 |
| **Nidum-Limitless-Gemma-2B-F16.gguf** | Full 16-bit floating point precision for maximum accuracy, ideal for high-end GPUs. |
|
| 34 |
|
| 35 |
+
## Quantized Model Versions:
|
| 36 |
+
|
| 37 |
+
Our unquantized model is available here: https://huggingface.co/nidum/Nidum-Limitless-Gemma-2B
|
| 38 |
+
|
| 39 |
## How to Use:
|
| 40 |
|
| 41 |
To get started with Nidum-Limitless-Gemma-2B-GGUF, you can use the following sample code for testing:
|