Update README.md
Browse files
README.md
CHANGED
|
@@ -32,7 +32,7 @@ quantized_by: fbaldassarri
|
|
| 32 |
Quantized version of [EleutherAI/pythia-2.8b](https://huggingface.co/fbaldassarri/EleutherAI/pythia-2.8b) using torch.float32 for quantization tuning.
|
| 33 |
- 8 bits (INT8)
|
| 34 |
- group size = 128
|
| 35 |
-
-
|
| 36 |
- Method AutoGPTQ
|
| 37 |
|
| 38 |
Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.5
|
|
|
|
| 32 |
Quantized version of [EleutherAI/pythia-2.8b](https://huggingface.co/fbaldassarri/EleutherAI/pythia-2.8b) using torch.float32 for quantization tuning.
|
| 33 |
- 8 bits (INT8)
|
| 34 |
- group size = 128
|
| 35 |
+
- Symmetrical Quantization
|
| 36 |
- Method AutoGPTQ
|
| 37 |
|
| 38 |
Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.5
|