avemio-digital commited on
Commit
5125af5
verified
1 Parent(s): 6709126

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -11
README.md CHANGED
@@ -21,10 +21,6 @@ tags:
21
  - Reasoning
22
  ---
23
 
24
-
25
- <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'"/>
26
-
27
-
28
  # German-RAG-PHI-3.5-MINI-4B-ORPO-HESSIAN-AI
29
 
30
  <!-- Provide a quick summary of what the model is/does. -->
@@ -251,6 +247,7 @@ It's important to note that the actual power consumption may vary depending on t
251
  | Model | GPU Type | Power Consumption From GPUs |
252
  |----------------|---------------------|-----------------------------|
253
  | German-RAG-PHI-ORPO | A100 ([Hessian AI supercomputer](https://hessian.ai/de/)) | 0.00921 MWh |
 
254
  ## Bias, Risks, and Limitations
255
 
256
  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.
@@ -259,13 +256,6 @@ Such content can also be produced unintentionally, especially in the case of bia
259
  Otherwise, many facts from German-RAG-PHI-ORPO or any LLM will often not be true, so they should be checked.
260
 
261
 
262
-
263
-
264
- ## Model Card Contact
265
-
266
-
267
- For errors in this model card, please contact ([[email protected]](mailto:[email protected])).
268
-
269
  ## The German-RAG AI Team
270
  [Marcel Rosiak](https://de.linkedin.com/in/marcel-rosiak)
271
  [Soumya Paul](https://de.linkedin.com/in/soumya-paul-1636a68a)
 
21
  - Reasoning
22
  ---
23
 
 
 
 
 
24
  # German-RAG-PHI-3.5-MINI-4B-ORPO-HESSIAN-AI
25
 
26
  <!-- Provide a quick summary of what the model is/does. -->
 
247
  | Model | GPU Type | Power Consumption From GPUs |
248
  |----------------|---------------------|-----------------------------|
249
  | German-RAG-PHI-ORPO | A100 ([Hessian AI supercomputer](https://hessian.ai/de/)) | 0.00921 MWh |
250
+
251
  ## Bias, Risks, and Limitations
252
 
253
  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.
 
256
  Otherwise, many facts from German-RAG-PHI-ORPO or any LLM will often not be true, so they should be checked.
257
 
258
 
 
 
 
 
 
 
 
259
  ## The German-RAG AI Team
260
  [Marcel Rosiak](https://de.linkedin.com/in/marcel-rosiak)
261
  [Soumya Paul](https://de.linkedin.com/in/soumya-paul-1636a68a)