https://github.com/estnafinema0/russian-jokes-generator
Transformer Models for Humorous Text Generation. Fine-tuned on Russian jokes dataset with ALiBi, RoPE, GQA, and SwiGLU.Plus a custom Byte-level BPE tokenizer.
https://github.com/estnafinema0/russian-jokes-generator
alibi bpe-tokenizer grouped-query-attention nlp pytorch rotary-position-embedding swiglu transformer-models
Last synced: 3 months ago
JSON representation
Transformer Models for Humorous Text Generation. Fine-tuned on Russian jokes dataset with ALiBi, RoPE, GQA, and SwiGLU.Plus a custom Byte-level BPE tokenizer.
- Host: GitHub
- URL: https://github.com/estnafinema0/russian-jokes-generator
- Owner: estnafinema0
- Created: 2025-03-10T20:57:31.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2025-03-10T21:07:02.000Z (3 months ago)
- Last Synced: 2025-03-10T22:19:27.767Z (3 months ago)
- Topics: alibi, bpe-tokenizer, grouped-query-attention, nlp, pytorch, rotary-position-embedding, swiglu, transformer-models
- Language: Jupyter Notebook
- Homepage: https://huggingface.co/estnafinema0/russian-jokes-generator
- Size: 294 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Russian Jokes Generator
This repository contains a set of Transformer-based language models fine-tuned on a dataset of Russian jokes (anecdotes). The models are designed to generate humorous and coherent Russian text. The repository includes three versions of the model: `nano`, `mini`, and `small`, each with different architectures and training configurations. Additionally, a custom Byte-level BPE tokenizer, trained on the Russian jokes dataset, is provided.
## Table of Contents
- [Model Details](#model-details)
- [Architecture](#architecture)
- [Training Details](#training-details)
- [Performance](#performance)
- [Usage](#usage)
- [Loading the Model](#loading-the-model)
- [Generating Text](#generating-text)
- [Examples](#examples)
- [Repository Structure](#repository-structure)
- [Jupyter Notebook](#jupyter-notebook)
- [License](#license)
## Model Details
### Architecture
The models are based on the Transformer architecture, enhanced with several advanced techniques:
1. Positional Embeddings: ALiBi (Attention with Linear Biases) and RoPE (Rotary Positional Embeddings) are used for positional encoding.
2. Attention Mechanism: Grouped-Query Attention (GQA) and Multi-Head Latent Attention (MHLA) are employed to improve efficiency and performance.
3. Activation Function: SwiGLU activation is used in the feed-forward layers.
Three versions of the model are available:
- **Nano**: 3 layers, 4 heads, 96 hidden dimensions.
- **Mini**: 6 layers, 6 heads, 384 hidden dimensions. Trained with RoPE and MHLA.
- **Small**: 12 layers, 12 heads, 768 hidden dimensions. Trained with RoPE and MHLA.
### Training Details
The models were trained on the [IgorVolochay/russian_jokes](https://huggingface.co/datasets/IgorVolochay/russian_jokes) dataset.
Key training parameters include:
1. Epochs: The number of full iterations over the dataset was determined by the `n_step` parameter in the Trainer initialization. The models were trained for 1 epoch (nano), 1 epoch (mini), and 6 epochs (small).
2. Batch Size: 32 for nano and mini models, 64 for the small model.
3. Learning Rate: 5e-4 with cosine decay for the small model, 3e-4 for the nano and mini models.
4. Loss Function: Cross-entropy loss was used for training.
5. Hardware: Training was conducted on an NVIDIA A100 GPU via Google Colab.
### Performance
The performance of each model is summarized below:
| Model | Training Loss (min) | Validation Loss (min) |
|-------|---------------------:|------------------------:|
| Nano | 3.784 | 3.932 |
| Mini | 3.127 | 3.144 |
| Small | 2.933 | 3.025 |
Training and validation loss curves for each model are provided below:
#### Nano Model
#### Mini Model
#### Small Model
## Usage
### Loading the Model
You can load the models and tokenizer from the Hugging Face Hub using the following code:
```python
# Small model
model_small = TransformerForCausalLM.from_pretrained("estnafinema0/russian-jokes-generator", revision="small")
tokenizer = ByteLevelBPETokenizer.from_pretrained("estnafinema0/russian-jokes-generator")
```
### Generating Text
To generate text using the model, you can use the following code:
```python
text = "Штирлиц пришел домой"
input_ids = torch.tensor(tokenizer.encode(text), device=device)
model_output = model_small.generate(
input_ids[None, :], max_new_tokens=200, eos_token_id=tokenizer.eos_token_id, do_sample=True, top_k=10
)
print(tokenizer.decode(model_output[0].tolist()))
```
## Examples
Here are some examples of jokes generated by the `small` model:
1. **Input**: "Пришел Петя в баню и говорит"
**Output**: "Пришел Петя в баню и говорит - Василий Иванович, вы знаете, кто я - Петя, или Петя? - Ахааха, и я - Ахаилая, я - Ахаил! - А какая Петя? - Я - Ахаилая! - Ну и я, когда я банкрот, банкротство, конечно..."
2. **Input**: "Вышел как-то на крыльцо"
**Output**: "Вышел как-то на крыльцо, а там плачет. Стукнулся: упал, выпал. Плачет – упал."
3. **Input**: "Священник задает ребёнку вопрос"
**Output**: "Священник задает ребёнку вопрос ему на ухо:- Что, братан, опять несёл?- Братан, ты что, братан, охуел?"
## Repository Structure
The repository is organized as follows:
- **Models**: Three versions of the model (`nano`, `mini`, `small`) are available in different branches:
- `main`: Nano model.
- `mini`: Mini model.
- `small`: Small model.
- **Tokenizer**: A custom Byte-level BPE tokenizer trained on the Russian jokes dataset.
- **Jupyter Notebook**: A detailed notebook containing the implementation, training, and evaluation of the models.
## Jupyter Notebook
The repository includes a Jupyter Notebook (`russian_jokes_generator.ipynb`) that provides a step-by-step guide to:
- Training the tokenizer.
- Implementing and training the Transformer models.
- Evaluating the models and generating text.
You can find the notebook in the repository and run it locally or in Google Colab.
P.S. Now the notebook is released in russian.
## License
This project is licensed under the Apache 2.0 License. See the [LICENSE](https://www.apache.org/licenses/LICENSE-2.0.txt) file for more details.
---
Thank you for your time!