Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,8 @@ license: apache-2.0
|
|
| 8 |
> The GGUF corresponds to Q3_K_S quantization.
|
| 9 |
>
|
| 10 |
> You can find the half-precision version [here](https://huggingface.co/RekaAI/reka-flash-3.1), and the Reka Quant quantization library [here](https://github.com/reka-ai/rekaquant)
|
|
|
|
|
|
|
| 11 |
|
| 12 |
## Quick Start
|
| 13 |
Reka Flash 3.1 Quantized is released in a llama.cpp-compatible Q3_K_S format. You may use any library compatible with GGUF to run the model.
|
|
|
|
| 8 |
> The GGUF corresponds to Q3_K_S quantization.
|
| 9 |
>
|
| 10 |
> You can find the half-precision version [here](https://huggingface.co/RekaAI/reka-flash-3.1), and the Reka Quant quantization library [here](https://github.com/reka-ai/rekaquant)
|
| 11 |
+
>
|
| 12 |
+
> [Learn more](https://reka.ai/news/reka-quantization-technology) about our quantization technology.
|
| 13 |
|
| 14 |
## Quick Start
|
| 15 |
Reka Flash 3.1 Quantized is released in a llama.cpp-compatible Q3_K_S format. You may use any library compatible with GGUF to run the model.
|