Update README.md
Browse files
README.md
CHANGED
@@ -17,10 +17,6 @@ tags:
|
|
17 |
- Reasoning
|
18 |
---
|
19 |
|
20 |
-
|
21 |
-
<img src="https://www.German-RAG.ai/wp-content/uploads/2024/12/German-RAG-ICON-TO-WORDLOGO-Animation_Loop-small-ezgif.com-video-to-gif-converter.gif" alt="German-RAG Logo" width="400" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
22 |
-
|
23 |
-
|
24 |
# German-RAG-PHI-3-mini-4B-CPT-HESSIAN-AI
|
25 |
|
26 |
<!-- Provide a quick summary of what the model is/does. -->
|
@@ -144,6 +140,7 @@ It's important to note that the actual power consumption may vary depending on t
|
|
144 |
| Model | GPU Type | Power Consumption From GPUs |
|
145 |
|----------------|---------------------|-----------------------------|
|
146 |
| German-RAG-PHI-CPT | A100 ([Hessian AI supercomputer](https://hessian.ai/de/)) | 0.00576MWh MWh |
|
|
|
147 |
## Bias, Risks, and Limitations
|
148 |
|
149 |
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.
|
@@ -153,12 +150,6 @@ Otherwise, many facts from German-RAG-MISTRAL-CPT or any LLM will often not be t
|
|
153 |
|
154 |
|
155 |
|
156 |
-
|
157 |
-
## Model Card Contact
|
158 |
-
|
159 |
-
|
160 |
-
For errors in this model card, please contact ([[email protected]](mailto:[email protected])).
|
161 |
-
|
162 |
## The German-RAG AI Team
|
163 |
[Marcel Rosiak](https://de.linkedin.com/in/marcel-rosiak)
|
164 |
[Soumya Paul](https://de.linkedin.com/in/soumya-paul-1636a68a)
|
|
|
17 |
- Reasoning
|
18 |
---
|
19 |
|
|
|
|
|
|
|
|
|
20 |
# German-RAG-PHI-3-mini-4B-CPT-HESSIAN-AI
|
21 |
|
22 |
<!-- Provide a quick summary of what the model is/does. -->
|
|
|
140 |
| Model | GPU Type | Power Consumption From GPUs |
|
141 |
|----------------|---------------------|-----------------------------|
|
142 |
| German-RAG-PHI-CPT | A100 ([Hessian AI supercomputer](https://hessian.ai/de/)) | 0.00576MWh MWh |
|
143 |
+
|
144 |
## Bias, Risks, and Limitations
|
145 |
|
146 |
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.
|
|
|
150 |
|
151 |
|
152 |
|
|
|
|
|
|
|
|
|
|
|
|
|
153 |
## The German-RAG AI Team
|
154 |
[Marcel Rosiak](https://de.linkedin.com/in/marcel-rosiak)
|
155 |
[Soumya Paul](https://de.linkedin.com/in/soumya-paul-1636a68a)
|