Update README.md
Browse files
README.md
CHANGED
|
@@ -2,7 +2,65 @@
|
|
| 2 |
license: bigscience-bloom-rail-1.0
|
| 3 |
datasets:
|
| 4 |
- dejanseo/good-vibes
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
pipeline_tag: text-classification
|
| 8 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: bigscience-bloom-rail-1.0
|
| 3 |
datasets:
|
| 4 |
- dejanseo/good-vibes
|
| 5 |
+
widget:
|
| 6 |
+
- example_title: Example 1
|
| 7 |
+
text: >-
|
| 8 |
+
The concert last night was an unforgettable experience filled with amazing
|
| 9 |
+
performances.
|
| 10 |
+
- example_title: Example 2
|
| 11 |
+
text: >-
|
| 12 |
+
I found the book to be quite insightful and it provided a lot of valuable
|
| 13 |
+
information.
|
| 14 |
+
- example_title: Example 3
|
| 15 |
+
text: The weather today is pretty average, not too hot and not too cold.
|
| 16 |
+
- example_title: Example 4
|
| 17 |
+
text: >-
|
| 18 |
+
Although the service was slow, the food at the restaurant was quite
|
| 19 |
+
enjoyable.
|
| 20 |
+
- example_title: Example 5
|
| 21 |
+
text: The new software update has caused more problems than it fixed.
|
| 22 |
+
- example_title: Example 6
|
| 23 |
+
text: The customer support team was unhelpful and I had a frustrating experience.
|
| 24 |
+
- example_title: Example 7
|
| 25 |
+
text: I had a fantastic time exploring the city and discovering new places.
|
| 26 |
+
- example_title: Example 8
|
| 27 |
+
text: The meeting was very productive and we accomplished all our goals.
|
| 28 |
+
- example_title: Example 9
|
| 29 |
+
text: This is the worst purchase I've ever made and I regret buying it.
|
| 30 |
+
- example_title: Example 10
|
| 31 |
+
text: >-
|
| 32 |
+
I am extremely pleased with the results of the project and how smoothly
|
| 33 |
+
everything went.
|
| 34 |
language:
|
| 35 |
- en
|
| 36 |
pipeline_tag: text-classification
|
| 37 |
+
---
|
| 38 |
+
|
| 39 |
+
Multi-label sentiment classification model developed by [Dejan Marketing](https://dejanmarketing.com/).
|
| 40 |
+
|
| 41 |
+
To see this model in action visit: [Good Vibes Tool](https://dejanmarketing.com/tools/good-vibes/)
|
| 42 |
+
|
| 43 |
+
The model is designed to be deployed in an automated pipeline capable of classifying text sentiment for thousands (or even millions) of text chunks or as a part of a scraping pipeline.
|
| 44 |
+
|
| 45 |
+
This is a demo model which may occassionally misclasify some texts. In a typical commercial project, a larger model is deployed for the task, and in special cases, a domain-specific model is developed for the client.
|
| 46 |
+
|
| 47 |
+
# Engage Our Team
|
| 48 |
+
Interested in using this in an automated pipeline for bulk URL and text processing?
|
| 49 |
+
|
| 50 |
+
Please [book an appointment](https://dejanmarketing.com/conference/) to discuss your needs.
|
| 51 |
+
|
| 52 |
+
# Base Model
|
| 53 |
+
|
| 54 |
+
albert/albert-base-v2
|
| 55 |
+
|
| 56 |
+
## Labels
|
| 57 |
+
```py
|
| 58 |
+
sentiment_labels = {
|
| 59 |
+
0: "Good Vibes",
|
| 60 |
+
1: "No Vibes",
|
| 61 |
+
2: "Bad Vibes"
|
| 62 |
+
}
|
| 63 |
+
```
|
| 64 |
+
# Sources of Training Data
|
| 65 |
+
|
| 66 |
+
Synthetic. Mistral.
|