Update README.md
Browse files
README.md
CHANGED
|
@@ -3,4 +3,10 @@ library_name: transformers
|
|
| 3 |
license: llama2
|
| 4 |
---
|
| 5 |
|
| 6 |
-
Converted version of [CodeLlama-70b](https://huggingface.co/meta-llama/CodeLlama-70b-hf) to 4-bit using bitsandbytes. For more information about the model, refer to the model's page.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
license: llama2
|
| 4 |
---
|
| 5 |
|
| 6 |
+
Converted version of [CodeLlama-70b](https://huggingface.co/meta-llama/CodeLlama-70b-hf) to 4-bit using bitsandbytes. For more information about the model, refer to the model's page.
|
| 7 |
+
|
| 8 |
+
## Impact on performance
|
| 9 |
+
|
| 10 |
+
In the following figure, we can see the impact on the performance of a set of models relative to the required RAM space. It is noticeable that the quantized models have equivalent performance while providing a significant gain in RAM usage.
|
| 11 |
+
|
| 12 |
+
|