PEFT
Safetensors
Ukrainian

Model Card for Model ID

Presented in Empowering Smaller Models: Tuning LLaMA and Gemma with Chain-of-Thought for Ukrainian Exam Tasks (arXiv:2503.13988)

PEFT 4bit tuning of google/gemma-2-9b-it on Ukrainian language and literature tasks of ZNO (EIE) & NMT dataset to generate step-by-step solution with task topic:

<bos><start_of_turn>user
Дайте розгорнуту відповідь на завдання, починаючи з ключового слова "Відповідь:" та використовуючи лише наведені нижче варіанти.

Завдання: З’ясуйте, якими частинами мови є виділені слова в реченні (цифра позначає наступне слово).
Сучасна людина, щоб бути (1)успішною, має вчитися (2)впродовж (3)усього життя, (4)опановуючи нові галузі знань.

Варіанти відповіді:
А – займенник
Б – прикметник
В – форма дієслова (дієприкметник)
Г – форма дієслова (дієприслівник)
Д – прийменник<end_of_turn>
<start_of_turn>model
Відповідь:
ТЕМА: Морфологія. Частини мови
Завдання перевіряє ваше вміння визначати частини мови.
Необхідно бути дуже уважним, тому що частиномовна приналежність конкретного слова часто залежить від контексту. Проаналізуймо кожне із запропонованих слів.
Слово успішною відповідає на питання яка? та вказує на ознаку предмета. Отже, це прикметник.
Слово впродовж не відповідає на питання, а лише поєднує слова в реченні. Отже, це прийменник.
Слово усього відповідає на питання що? і вказує на предмет. Отже, це займенник.
А от слово опановуючи відповідає на питання що роблячи? та вказує на додаткову дію. Отже, це особлива форма дієслова дієприслівник.
Відповідь: 1 – Б, 2 – Д, 3 – А, 4 – Г.<end_of_turn>

Model Details

Model Description

  • Developed by: [More Information Needed]
  • Funded by [optional]: [More Information Needed]
  • Shared by [optional]: [More Information Needed]
  • Model type: [More Information Needed]
  • Language(s) (NLP): [More Information Needed]
  • License: [More Information Needed]
  • Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

  • Repository: [More Information Needed]
  • Paper [optional]: [More Information Needed]
  • Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

  • Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

  • Hardware Type: [More Information Needed]
  • Hours used: [More Information Needed]
  • Cloud Provider: [More Information Needed]
  • Compute Region: [More Information Needed]
  • Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Framework versions

  • PEFT 0.14.0
Downloads last month
10
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for NLPForUA/gemma-2-it-zno-cot-with-topic

Base model

google/gemma-2-9b
Adapter
(77)
this model

Collection including NLPForUA/gemma-2-it-zno-cot-with-topic