Mistral-7B-UK is a Large Language Model finetuned for the Ukrainian language.
Mistral-7B-UK is trained using the following formula:
Initial finetuning of Mistral-7B-v0.2 using structured and unstructured datasets.
SLERP merge of the finetuned model with a model that performs better than Mistral-7B-v0.2 on OpenLLM benchmark: NeuralTrix-7B
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 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:
1!pip install -qU transformers accelerate
23from transformers import AutoTokenizer
4import transformers
5import torch
67model ="SherlockAssistant/Mistral-7B-Instruct-Ukrainian"8messages =[{"role":"user","content":"What is a large language model?"}]910tokenizer = AutoTokenizer.from_pretrained(model)11prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)12pipeline = transformers.pipeline(13"text-generation",14 model=model,15 torch_dtype=torch.bfloat16,16 device_map="auto",17)1819outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)20print(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
1@inproceedings{boros-chivereanu-dumitrescu-purcaru-2024-llm-uk,
2 title = "Fine-tuning and Retrieval Augmented Generation for Question Answering using affordable Large Language Models",
3 author = "Boros, Tiberiu and Chivereanu, Radu and Dumitrescu, Stefan Daniel and Purcaru, Octavian",
4 booktitle = "Proceedings of the Third Ukrainian Natural Language Processing Workshop, LREC-COLING",
5 month = may,
6 year = "2024",
7 address = "Torino, Italy",
8 publisher = "European Language Resources Association",
9}
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.
