Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,19 @@ tags: []
|
|
| 10 |
|
| 11 |
|
| 12 |
## Model Details
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
### Model Description
|
| 15 |
|
|
|
|
| 10 |
|
| 11 |
|
| 12 |
## Model Details
|
| 13 |
+
Hardware - 1 × T4 GPU (Available on Colab)
|
| 14 |
+
|
| 15 |
+
Quantized Results
|
| 16 |
+
- 'perplexity': 43.54572677612305
|
| 17 |
+
- 'latency (s/sample)': 0.06516031932830811
|
| 18 |
+
- 'tokens/sec': 1452.1107473899917,
|
| 19 |
+
- 'model size (MB)': 1002.12890625
|
| 20 |
+
|
| 21 |
+
Base Results
|
| 22 |
+
- 'perplexity': 34.53372573852539,
|
| 23 |
+
- 'latency (s/sample)': 0.024253430366516112
|
| 24 |
+
- 'tokens/sec': 3901.303797859078
|
| 25 |
+
- 'model size (MB)': 5716.2578125
|
| 26 |
|
| 27 |
### Model Description
|
| 28 |
|