---
license: llama2
language:
- hu
- en
tags:
- puli
---

# PULI LlumiX 32K (6.74B billion parameter)

For further details or testing our instruct model, see [our demo site](https://puli.nytud.hu/puli-llumix-instruct).

  - Trained with OpenChatKit [github](https://github.com/togethercomputer/OpenChatKit)
  - The [LLaMA-2-7B-32K](https://huggingface.co/togethercomputer/LLaMA-2-7B-32K) model were continuously pretrained on Hungarian dataset
  - The model has been extended to a context length of 32K with position interpolation
  - Checkpoint: 100 000 steps

## Dataset for continued pretraining

- Hungarian: 7.9 billion words, documents (763K) that exceed 5000 words in length
- English: Long Context QA (2 billion words), BookSum (78 million words)

## Limitations

- max_seq_length = 32 768
- float16
- vocab size: 32 000

## Usage with pipeline

```python
from transformers import pipeline, LlamaForCausalLM, LlamaTokenizer

model = LlamaForCausalLM.from_pretrained("NYTK/PULI-LlumiX-32K")
tokenizer = LlamaTokenizer.from_pretrained("NYTK/PULI-LlumiX-32K")
prompt = "Elmesélek egy történetet a nyelvtechnológiáról."
generator = pipeline(task="text-generation", model=model, tokenizer=tokenizer)

print(generator(prompt, max_new_tokens=30)[0]["generated_text"])
```