|
--- |
|
tags: |
|
- generated_from_trainer |
|
- not-for-all-audiences |
|
model-index: |
|
- name: TinySatirik-m |
|
results: [] |
|
license: mit |
|
datasets: |
|
- igorktech/anekdots |
|
language: |
|
- ru |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# TinySatirik-m |
|
|
|
This model is a pre-trained version of really tiny LLama2 model on an [anekdots](https://huggingface.co/datasets/igorktech/anekdots) dataset. |
|
|
|
Inspired by [TinyStories](https://arxiv.org/abs/2305.07759). |
|
|
|
## Tokenizer |
|
|
|
To utilize the model, install the [special tokenizer](https://github.com/Koziev/character-tokenizer): |
|
|
|
```bash |
|
pip install git+https://github.com/Koziev/character-tokenizer |
|
``` |
|
|
|
In addition to recognizing Cyrillic characters and punctuation, this tokenizer is aware of special tokens such as ```<s>```, ```</s>```, ```<pad>```, and ```<unk>```. |
|
|
|
As this is a non-standard tokenizer for transformers, load it not via ```transformers.AutoTokenizer.from_pretrained```, but somewhat like this: |
|
|
|
```python |
|
import charactertokenizer |
|
|
|
... |
|
tokenizer = charactertokenizer.CharacterTokenizer.from_pretrained('igorktech/CharPicoSatirik-m') |
|
``` |
|
|
|
To observe tokenization, use this code snippet: |
|
|
|
```python |
|
prompt = '<s>Hello World\n' |
|
encoded_prompt = tokenizer.encode(prompt, return_tensors='pt') |
|
print('Tokenized prompt:', ' | '.join(tokenizer.decode([t]) for t in encoded_prompt[0])) |
|
``` |
|
|
|
You will see a list of tokens separated by the ```|``` symbol: |
|
|
|
``` |
|
Tokenized prompt: <s> | H | e | l | l | o | | W | o | r | l | d | |
|
``` |
|
|
|
Tokenizer created by [Koziev](https://github.com/Koziev). |
|
|
|
## Model description |
|
|
|
Llama2 architecture based. |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0005 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 250 |
|
- num_epochs: 2 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
