bjoernp commited on
Commit
9c4b5bf
1 Parent(s): 795c9ca

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -45,6 +45,8 @@ The model performs exceptionally well on writing, explanation and discussion tas
45
  "average": 6.8875
46
  }
47
  ```
 
 
48
 
49
  ## Model Details
50
 
@@ -114,6 +116,9 @@ in advance, and the model may in some instances produce inaccurate, biased or ot
114
  to user prompts. Therefore, before deploying any applications of `LeoLM/leo-hessianai-70b-chat`, developers should
115
  perform safety testing and tuning tailored to their specific applications of the model.
116
 
 
 
 
117
  Please see Meta's [Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/).
118
 
119
  ## Finetuning Details
 
45
  "average": 6.8875
46
  }
47
  ```
48
+ Have a look at some examples [in this Google Doc](https://docs.google.com/document/d/1SAAikkPAF4oLoFISqE0P1mRL5OUk8l2pI90zZC4bP1E/edit?usp=sharing).
49
+
50
 
51
  ## Model Details
52
 
 
116
  to user prompts. Therefore, before deploying any applications of `LeoLM/leo-hessianai-70b-chat`, developers should
117
  perform safety testing and tuning tailored to their specific applications of the model.
118
 
119
+ We are aware of the model refusing to answer more often than desired. This will be adressed in future versions. For now, the training
120
+ dataset is equal to that used for our smaller chat variants.
121
+
122
  Please see Meta's [Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/).
123
 
124
  ## Finetuning Details