|
--- |
|
language: en |
|
tags: |
|
- autotrain |
|
- text-generation |
|
- llm |
|
- memes |
|
library_name: transformers |
|
library_version: [latest version at the time of training] |
|
model_type: llama 2 |
|
widget: |
|
- text: "When you try to code without coffee, " |
|
--- |
|
|
|
# Llama 2 Meme Generator |
|
|
|
## Model Description |
|
|
|
This model is a fine-tuned version of the `llama 2` model, specifically tailored for generating meme captions. It captures the essence and humor commonly found in popular internet memes and offers a unique approach to meme creation. Just provide a prompt or a meme context, and let the model generate a fitting caption! |
|
|
|
## Training Data |
|
|
|
The model was trained using a diverse dataset of meme captions, spanning various internet trends, jokes, and pop culture references. This ensures a wide range of meme generation capabilities, from classic meme formats to contemporary internet humor. |
|
|
|
## Training Procedure |
|
|
|
The model was fine-tuned using the `autotrain llm` command with optimal hyperparameters for meme generation. Special care was taken to avoid overfitting, ensuring the model can generalize well across various meme contexts. |
|
|
|
## Usage |
|
|
|
To generate a meme caption using this model, you can use the following code: |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelWithLMHead |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("bickett/meme-llama") |
|
model = AutoModelWithLMHead.from_pretrained("bickett/meme-llama") |
|
|
|
input_text = "When you try to code without coffee" |
|
input_ids = tokenizer.encode(input_text, return_tensors="pt") |
|
output = model.generate(input_ids) |
|
|
|
print(tokenizer.decode(output[0], skip_special_tokens=True)) |
|
|
