alexmarques
commited on
Commit
•
0c8a3b8
1
Parent(s):
0f03d3a
Update README.md
Browse files
README.md
CHANGED
@@ -35,7 +35,7 @@ base_model: meta-llama/Llama-3.2-1B-Instruct
|
|
35 |
- **Model Developers:** Neural Magic
|
36 |
|
37 |
Quantized version of [Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct).
|
38 |
-
It achieves scores within
|
39 |
|
40 |
### Model Optimizations
|
41 |
|
|
|
35 |
- **Model Developers:** Neural Magic
|
36 |
|
37 |
Quantized version of [Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct).
|
38 |
+
It achieves scores within 5% of the scores of the unquantized model for MMLU, ARC-Challenge, GSM-8k, Hellaswag, Winogrande and TruthfulQA.
|
39 |
|
40 |
### Model Optimizations
|
41 |
|