|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- allenai/MADLAD-400 |
|
- eryk-mazus/polka-pretrain-en-pl-v1 |
|
language: |
|
- pl |
|
- en |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
 |
|
|
|
# Polka-1.1b |
|
|
|
|
|
`polka-1.1b` takes the [TinyLlama-1.1B](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) model and enhances it by continuing pretraining on an additional **5.7 billion Polish tokens**, primarily sourced from the [MADLAD-400](https://arxiv.org/abs/2309.04662) dataset. The tokens were sampled in a 10:1 ratio between Polish and English shards using [DSIR](https://github.com/p-lambda/dsir). Furthermore, Polka extends the TinyLlama tokenizer's vocabulary to 43,882 tokens, improving its efficiency for generating Polish text. |
|
|
|
The training took 425 RTX 4090 GPU hours on a single 8 x RTX 4090 machine with DeepSpeed ZeRO-2. |
|
|
|
## Notes |
|
|
|
... |
|
|
|
## Sample code |
|
|
|
```python |
|
... |
|
``` |
