Youtube shorts comment generator ๐Ÿง  (I couldn't come up with a more original name)

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.

Model Details ๐Ÿ”ฅ

  • Parameters: 82M (DistilGPT2 architecture)
  • Training Data: 1,475,500 YouTube Shorts comments
  • Special Skills: Emoji generation, broken English, random character generation

Usage Example ๐Ÿ

from transformers import pipeline

brainrot = pipeline('text-generation', model='PingVortex/Youtube-shorts-comment-generator')

output = brainrot("When you see a Sigma edit:", max_length=50)
print(output[0]['generated_text'])

Sample output:
"When you see a Sigma edit: ๐Ÿ˜‚๐Ÿ˜‚๐Ÿ˜‚๐Ÿ˜‚ The white one on the last pic?๐Ÿ˜‚๐Ÿ˜‚๐Ÿ˜‚๐Ÿ˜…๐Ÿ˜…๐Ÿ˜…๐Ÿ˜Š๐Ÿ˜Š๐Ÿ˜Š๐Ÿ˜…๐Ÿ˜ฎ๐Ÿ˜ฎ๐Ÿ˜…"

Training Info โš™๏ธ

  • Epochs: 1
  • Batch Size: 8
  • Hardware: Google Colab T4 GPU
  • Training Time: ~2 hours
  • Loss: 0.24

Ethical Considerations โš ๏ธ

This model may generate:

  • Extreme emoji spam (๐Ÿ”ฅ๐Ÿ’€๐Ÿคฃ)
  • Nonsensical combinations
  • Mild brain damage
  • Occasional coherent text

Use responsibly (or irresponsibly, we don't judge).

License ๐Ÿ“œ

CC0 1.0 Universal (Public Domain)

Downloads last month
23
Safetensors
Model size
81.9M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for PingVortex/Youtube-shorts-comment-generator

Finetuned
(1340)
this model
Quantizations
1 model

Dataset used to train PingVortex/Youtube-shorts-comment-generator