Update README.md
Browse files
README.md
CHANGED
|
@@ -38,8 +38,6 @@ Quantized version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/m
|
|
| 38 |
- group size = 128
|
| 39 |
- Symmetrical Quantization
|
| 40 |
- Method WoQ (AutoRound format)
|
| 41 |
-
|
| 42 |
-
Fast and low memory, 2-3X speedup (slight accuracy drop at W4G128)
|
| 43 |
|
| 44 |
Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round)
|
| 45 |
|
|
|
|
| 38 |
- group size = 128
|
| 39 |
- Symmetrical Quantization
|
| 40 |
- Method WoQ (AutoRound format)
|
|
|
|
|
|
|
| 41 |
|
| 42 |
Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round)
|
| 43 |
|