Update README.md
Browse files
README.md
CHANGED
|
@@ -153,10 +153,9 @@ GRAG-PHI-SFT, running on NVIDIA A100 with 8 GPUs for 5 days, has an approximate
|
|
| 153 |
|
| 154 |
It's important to note that the actual power consumption may vary depending on the specific workload and operational conditions. For accurate power consumption measurements, using dedicated power monitoring tools is recommended.
|
| 155 |
|
| 156 |
-
|
|
| 157 |
-
|
| 158 |
-
| GRAG-PHI-SFT
|
| 159 |
-
|
| 160 |
## Bias, Risks, and Limitations
|
| 161 |
|
| 162 |
Like any base language model or fine-tuned model without safety filtering, it is relatively easy for a user to prompt these models to generate harmful and generally sensitive content.
|
|
|
|
| 153 |
|
| 154 |
It's important to note that the actual power consumption may vary depending on the specific workload and operational conditions. For accurate power consumption measurements, using dedicated power monitoring tools is recommended.
|
| 155 |
|
| 156 |
+
| Model | GPU Type | Power Consumption From GPUs |
|
| 157 |
+
|----------------|---------------------|-----------------------------|
|
| 158 |
+
| GRAG-PHI-SFT | A100 ([Hessen AI supercomputer](https://hessian.ai/de/)) | 0.288 MWh |
|
|
|
|
| 159 |
## Bias, Risks, and Limitations
|
| 160 |
|
| 161 |
Like any base language model or fine-tuned model without safety filtering, it is relatively easy for a user to prompt these models to generate harmful and generally sensitive content.
|