|
--- |
|
base_model: INSAIT-Institute/BgGPT-7B-Instruct-v0.2 |
|
library_name: peft |
|
license: apache-2.0 |
|
language: |
|
- bg |
|
tags: |
|
- propaganda |
|
--- |
|
|
|
# Model Card for identrics/BG_propaganda_detector |
|
|
|
|
|
## Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
|
|
|
|
- **Developed by:** Identrics |
|
- **Language:** Bulgarian |
|
- **License:** apache-2.0 |
|
- **Finetuned from model:** INSAIT-Institute/BgGPT-7B-Instruct-v0.2 |
|
|
|
|
|
|
|
## Uses |
|
|
|
To be used as a binary classifier to identify if propaganda is present in a string containing a comment from a social media site |
|
|
|
### Example |
|
|
|
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> |
|
|
|
|
|
## Training Details |
|
|
|
|
|
|
|
Trained on a corpus of 200 human-generated comments, augmented with 200 more synthetic comments... |
|
|
|
Achieved an f1 score of x% |
|
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> |
|
|
|
|
|
|
|
|
|
|
|
- PEFT 0.11.1 |
