105 lines
4.4 KiB
Markdown
105 lines
4.4 KiB
Markdown
|
---
|
|||
|
|
library_name: transformers
|
|||
|
|
license: apache-2.0
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# Model card for Mistral-7B-Instruct-Ukrainian
|
|||
|
|
|
|||
|
|
Mistral-7B-UK is a Large Language Model finetuned for the Ukrainian language.
|
|||
|
|
|
|||
|
|
Mistral-7B-UK is trained using the following formula:
|
|||
|
|
1. Initial finetuning of [Mistral-7B-v0.2](mistralai/Mistral-7B-Instruct-v0.2) using structured and unstructured datasets.
|
|||
|
|
2. SLERP merge of the finetuned model with a model that performs better than `Mistral-7B-v0.2` on `OpenLLM` benchmark: [NeuralTrix-7B](https://huggingface.co/CultriX/NeuralTrix-7B-v1)
|
|||
|
|
3. DPO of the final model.
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
## Instruction format
|
|||
|
|
|
|||
|
|
In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens.
|
|||
|
|
|
|||
|
|
E.g.
|
|||
|
|
```
|
|||
|
|
text = "[INST]Відповідайте лише буквою правильної відповіді: Елементи експресіонізму наявні у творі: A. «Камінний хрест», B. «Інститутка», C. «Маруся», D. «Людина»[/INST]"
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:
|
|||
|
|
|
|||
|
|
## Model Architecture
|
|||
|
|
This instruction model is based on Mistral-7B-v0.2, a transformer model with the following architecture choices:
|
|||
|
|
- Grouped-Query Attention
|
|||
|
|
- Sliding-Window Attention
|
|||
|
|
- Byte-fallback BPE tokenizer
|
|||
|
|
|
|||
|
|
## Datasets - Structured
|
|||
|
|
- [UA-SQUAD](https://huggingface.co/datasets/FIdo-AI/ua-squad/resolve/main/ua_squad_dataset.json)
|
|||
|
|
- [Ukrainian StackExchange](https://huggingface.co/datasets/zeusfsx/ukrainian-stackexchange)
|
|||
|
|
- [UAlpaca Dataset](https://github.com/robinhad/kruk/blob/main/data/cc-by-nc/alpaca_data_translated.json)
|
|||
|
|
- [Ukrainian Subset from Belebele Dataset](https://github.com/facebookresearch/belebele)
|
|||
|
|
- [Ukrainian Subset from XQA](https://github.com/thunlp/XQA)
|
|||
|
|
- [ZNO Dataset provided in UNLP 2024 shared task](https://github.com/unlp-workshop/unlp-2024-shared-task/blob/main/data/zno.train.jsonl)
|
|||
|
|
|
|||
|
|
## Datasets - Unstructured
|
|||
|
|
- Ukrainian Wiki
|
|||
|
|
|
|||
|
|
## Datasets - DPO
|
|||
|
|
- Ukrainian translation of [distilabel-indel-orca-dpo-pairs](https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs)
|
|||
|
|
|
|||
|
|
## 💻 Usage
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
!pip install -qU transformers accelerate
|
|||
|
|
|
|||
|
|
from transformers import AutoTokenizer
|
|||
|
|
import transformers
|
|||
|
|
import torch
|
|||
|
|
|
|||
|
|
model = "SherlockAssistant/Mistral-7B-Instruct-Ukrainian"
|
|||
|
|
messages = [{"role": "user", "content": "What is a large language model?"}]
|
|||
|
|
|
|||
|
|
tokenizer = AutoTokenizer.from_pretrained(model)
|
|||
|
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|||
|
|
pipeline = transformers.pipeline(
|
|||
|
|
"text-generation",
|
|||
|
|
model=model,
|
|||
|
|
torch_dtype=torch.bfloat16,
|
|||
|
|
device_map="auto",
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
|||
|
|
print(outputs[0]["generated_text"])
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## Citation
|
|||
|
|
|
|||
|
|
If you are using this model in your research and publishing a paper, please help by citing our paper:
|
|||
|
|
|
|||
|
|
**BIB**
|
|||
|
|
|
|||
|
|
```bib
|
|||
|
|
@inproceedings{boros-chivereanu-dumitrescu-purcaru-2024-llm-uk,
|
|||
|
|
title = "Fine-tuning and Retrieval Augmented Generation for Question Answering using affordable Large Language Models",
|
|||
|
|
author = "Boros, Tiberiu and Chivereanu, Radu and Dumitrescu, Stefan Daniel and Purcaru, Octavian",
|
|||
|
|
booktitle = "Proceedings of the Third Ukrainian Natural Language Processing Workshop, LREC-COLING",
|
|||
|
|
month = may,
|
|||
|
|
year = "2024",
|
|||
|
|
address = "Torino, Italy",
|
|||
|
|
publisher = "European Language Resources Association",
|
|||
|
|
}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
**APA**
|
|||
|
|
|
|||
|
|
Boros, T., Chivereanu, R., Dumitrescu, S., & Purcaru, O. (2024). Fine-tuning and Retrieval Augmented Generation for Question Answering using affordable Large Language Models. In Proceedings of the Third Ukrainian Natural Language Processing Workshop, LREC-COLING. European Language Resources Association.
|
|||
|
|
|
|||
|
|
**MLA**
|
|||
|
|
|
|||
|
|
Boros, Tiberiu, Radu, Chivereanu, Stefan Daniel, Dumitrescu, Octavian, Purcaru. "Fine-tuning and Retrieval Augmented Generation for Question Answering using affordable Large Language Models." Proceedings of the Third Ukrainian Natural Language Processing Workshop, LREC-COLING. European Language Resources Association, 2024.
|
|||
|
|
|
|||
|
|
**Chicago**
|
|||
|
|
|
|||
|
|
Boros, Tiberiu, Radu, Chivereanu, Stefan Daniel, Dumitrescu, and Octavian, Purcaru. "Fine-tuning and Retrieval Augmented Generation for Question Answering using affordable Large Language Models." . In Proceedings of the Third Ukrainian Natural Language Processing Workshop, LREC-COLING. European Language Resources Association, 2024.
|
|||
|
|
|