---
license: apache-2.0
base_model: eryk-mazus/tinyllama-with-custom-tokenizer
datasets:
- allenai/MADLAD-400
- eryk-mazus/polka-pretrain-en-pl-v1
language:
- pl
- en
pipeline_tag: text-generation
widget:
  - text: "Wiedźmin 3 to fabularna gra akcji wyprodukowana"
    output:
      text: "..."
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/61bf0e11c88f3fd22f654059/EMSrPEzAFkjY9nvbaJoC3.png)

# 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 GPU hours on a single 8 x RTX 4090 machine with DeepSpeed ZeRO-2.

## Notes

...

## Sample code

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "eryk-mazus/polka-1.1b"

tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side="left")
tokenizer.pad_token = tokenizer.eos_token

model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", load_in_8bit=True)

prompt = """..."""

model_inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
generated_ids = model.generate(**model_inputs, max_new_tokens=512, do_sample=True, penalty_alpha=0.6, top_k=5)

output = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(output)
```