avemio
/

German-RAG-NEMO-12B-ORPO-HESSIAN-AI

Question Answering

Question-Answering

Model card Files Files and versions Community

avemio-digital commited on Jan 9

Commit

9486361

·

verified ·

1 Parent(s): 8563d3c

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -230,13 +230,13 @@ The subsets can be for this training step are derived from 3 different sources:
 ## Environmental Impact
-GRAG-NEMO-ORPO, running on NVIDIA A100 with 8 GPUs for 5 days, has an approximate power consumption as follows:
 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.
 | Model          | GPU Type            | Power Consumption From GPUs |
 |----------------|---------------------|-----------------------------|
-| GRAG-NEMO-ORPO   | A100 ([Hessian AI supercomputer](https://hessian.ai/de/)) | 0.288 MWh                    |
 ## Bias, Risks, and Limitations
 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.

 ## Environmental Impact
+GRAG-NEMO-ORPO, running on NVIDIA A100 with 80 GPUs for 4 days, has an approximate power consumption as follows:
 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.
 | Model          | GPU Type            | Power Consumption From GPUs |
 |----------------|---------------------|-----------------------------|
+| GRAG-NEMO-ORPO   | A100 ([Hessian AI supercomputer](https://hessian.ai/de/)) | 0.01843 MWh                    |
 ## Bias, Risks, and Limitations
 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.