Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,8 @@ pipeline_tag: text-generation
|
|
| 17 |
# Bielik-11B-v2.2-Instruct-Quanto-8bit
|
| 18 |
This model was converted to Quanto format from [SpeakLeash](https://speakleash.org/)'s [Bielik-11B-v.2.2-Instruct](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct).
|
| 19 |
|
|
|
|
|
|
|
| 20 |
## About Quanto
|
| 21 |
Optimum Quanto is a pytorch quantization backend for optimum. Model can be loaded using:
|
| 22 |
|
|
|
|
| 17 |
# Bielik-11B-v2.2-Instruct-Quanto-8bit
|
| 18 |
This model was converted to Quanto format from [SpeakLeash](https://speakleash.org/)'s [Bielik-11B-v.2.2-Instruct](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct).
|
| 19 |
|
| 20 |
+
**DISCLAIMER: Be aware that quantised models show reduced response quality and possible hallucinations!**
|
| 21 |
+
|
| 22 |
## About Quanto
|
| 23 |
Optimum Quanto is a pytorch quantization backend for optimum. Model can be loaded using:
|
| 24 |
|