SimuIation commited on
Commit
6f51415
·
verified ·
1 Parent(s): 6844a22

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -3
README.md CHANGED
@@ -31,8 +31,12 @@ The Digital Navigator model is designed to assist users by generating natural la
31
 
32
  ### Direct Use
33
 
34
- Users do not have much of a choice but only use it for experimental and educational purposes, since the model was fine-tuned for specific answers and question related to the Department of Communication and Digital Media website: https://cdm.uowm.gr/en/index/.
35
 
 
 
 
 
36
  ### Out-of-Scope Use
37
 
38
  - Generating harmful, biased, or misleading content
@@ -66,7 +70,7 @@ The model was trained using standard procedures for fine-tuning GPT-2 models.
66
 
67
  #### Training Hyperparameters
68
 
69
- - **Training regime:** [More Information Needed]
70
  - Learning Rate: 5e-5
71
  - Batch Size: 16
72
  - Epochs: 30
@@ -97,7 +101,7 @@ Due to the high complexity and small variety of the data:
97
 
98
  - **Hardware Type:** NVIDIA T4
99
  - **Hours used:** 18 minutes and 47 seconds
100
- - **Cloud Provider:** Google Collab
101
 
102
 
103
 
 
31
 
32
  ### Direct Use
33
 
34
+ The Digital Navigator model can be directly used for generating conversational responses in English. It is intended for use in chatbots, virtual assistants, and other applications requiring natural language understanding and generation.
35
 
36
+ - Conversational AI
37
+ - Customer Support
38
+ - Virtual Assistance
39
+
40
  ### Out-of-Scope Use
41
 
42
  - Generating harmful, biased, or misleading content
 
70
 
71
  #### Training Hyperparameters
72
 
73
+ - **Training regime:** fp32
74
  - Learning Rate: 5e-5
75
  - Batch Size: 16
76
  - Epochs: 30
 
101
 
102
  - **Hardware Type:** NVIDIA T4
103
  - **Hours used:** 18 minutes and 47 seconds
104
+ - **Cloud Provider:** Google Colab
105
 
106
 
107