library_name: transformers
license: cc-by-nc-4.0
language:
- en
- zh
base_model:
- meta-llama/Llama-3.2-3B-Instruct
pipeline_tag: text-generation
Kyara: Knowledge Yielding Adaptive Retrieval Augmentation for LLM Fine-tuning
π€ Hugging Face ο½ πGithub ο½ π Paper ο½ π English ο½ π Chinese ο½ π» Kaggle Notebook
Kyara (Knowledge Yielding Adaptive Retrieval Augmentation) is an experimental project aimed at improving language models through knowledge retrieval processes. The project seeks to enhance the modelβs ability to adapt knowledge and improve language comprehension, particularly in underrepresented languages like Traditional Chinese. Given the relatively scarce availability of Traditional Chinese data compared to the vast corpus of English data used for model training, Kyara addresses this gap by expanding the limited corpus for this language.
This is a preview model, with the stable version set to be released soon.
Benchmark
All evaluations are conducted in a zero-shot setting.
| Metric | Kyara-3b-it | Llama3.2-3b-it |
|---|---|---|
| TMMLUPlus | 42.54 | 40.01 |
| β- STEM | 45.17 | 40.37 |
| β- Humanities | 39.66 | 38.65 |
| β- Other | 41.18 | 39.06 |
| β- Social-Science | 44.16 | 41.98 |
| MMLU-Redux | 57.24 | 56.91 |
| GSM8K | 67.25 | 57.16 |
| MATH-L5 | 19.97 | 16.23 |
| CRUX | 31.25 | 25.25 |
| AlpacaEval | 23.87 | 19.35 |