Update README.md
Browse files
README.md
CHANGED
|
@@ -20,21 +20,17 @@ pipeline_tag: text-generation
|
|
| 20 |
library_name: transformers
|
| 21 |
---
|
| 22 |
|
| 23 |
-
# Youtube shorts comment generator
|
| 24 |
-
|
| 25 |
-
A **fine-tuned DistilGPT2 model** trained on 1.4M+ YouTube Shorts comments - the perfect language model for generating cursed internet humor, emoji spam, and authentic YouTube degeneracy.
|
| 26 |
|
| 27 |
- Base model: [distilgpt2](https://huggingface.co/distilgpt2)
|
| 28 |
- Trained on: [YouTube Shorts Comments Dataset](https://huggingface.co/datasets/PingVortex/Youtube_shorts_comments)
|
| 29 |
-
- Creator: [PingVortex](https://github.com/PingVortex)
|
| 30 |
|
| 31 |
-
## Model Details
|
| 32 |
|
| 33 |
- **Parameters**: 82M (DistilGPT2 architecture)
|
| 34 |
- **Training Data**: 1,475,500 YouTube Shorts comments
|
| 35 |
-
- **Special Skills**: Emoji generation, broken English, random character generation
|
| 36 |
|
| 37 |
-
## Usage Example
|
| 38 |
|
| 39 |
```python
|
| 40 |
from transformers import pipeline
|
|
@@ -48,24 +44,10 @@ print(output[0]['generated_text'])
|
|
| 48 |
*Sample output:*
|
| 49 |
`"When you see a Sigma edit: 😂😂😂😂 The white one on the last pic?😂😂😂😅😅😅😊😊😊😅😮😮😅"`
|
| 50 |
|
| 51 |
-
## Training Info
|
| 52 |
|
| 53 |
- **Epochs**: 1
|
| 54 |
- **Batch Size**: 8
|
| 55 |
- **Hardware**: Google Colab T4 GPU
|
| 56 |
- **Training Time**: ~2 hours
|
| 57 |
-
- **Loss**: 0.24
|
| 58 |
-
|
| 59 |
-
## Ethical Considerations ⚠️
|
| 60 |
-
|
| 61 |
-
This model may generate:
|
| 62 |
-
- Extreme emoji spam (🔥💀🤣)
|
| 63 |
-
- Nonsensical combinations
|
| 64 |
-
- Mild brain damage
|
| 65 |
-
- Occasional coherent text
|
| 66 |
-
|
| 67 |
-
Use responsibly (or irresponsibly, we don't judge).
|
| 68 |
-
|
| 69 |
-
## License 📜
|
| 70 |
-
|
| 71 |
-
**CC0 1.0 Universal** (Public Domain)
|
|
|
|
| 20 |
library_name: transformers
|
| 21 |
---
|
| 22 |
|
| 23 |
+
# Youtube shorts comment generator
|
|
|
|
|
|
|
| 24 |
|
| 25 |
- Base model: [distilgpt2](https://huggingface.co/distilgpt2)
|
| 26 |
- Trained on: [YouTube Shorts Comments Dataset](https://huggingface.co/datasets/PingVortex/Youtube_shorts_comments)
|
|
|
|
| 27 |
|
| 28 |
+
## Model Details
|
| 29 |
|
| 30 |
- **Parameters**: 82M (DistilGPT2 architecture)
|
| 31 |
- **Training Data**: 1,475,500 YouTube Shorts comments
|
|
|
|
| 32 |
|
| 33 |
+
## Usage Example
|
| 34 |
|
| 35 |
```python
|
| 36 |
from transformers import pipeline
|
|
|
|
| 44 |
*Sample output:*
|
| 45 |
`"When you see a Sigma edit: 😂😂😂😂 The white one on the last pic?😂😂😂😅😅😅😊😊😊😅😮😮😅"`
|
| 46 |
|
| 47 |
+
## Training Info
|
| 48 |
|
| 49 |
- **Epochs**: 1
|
| 50 |
- **Batch Size**: 8
|
| 51 |
- **Hardware**: Google Colab T4 GPU
|
| 52 |
- **Training Time**: ~2 hours
|
| 53 |
+
- **Loss**: 0.24
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|