Instructions to use G37A/Qwen3-Reranker-8B-squad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use G37A/Qwen3-Reranker-8B-squad with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("G37A/Qwen3-Reranker-8B-squad") model = AutoModelForCausalLM.from_pretrained("G37A/Qwen3-Reranker-8B-squad") - Notebooks
- Google Colab
- Kaggle
| language: | |
| - uk | |
| license: apache-2.0 | |
| library_name: transformers | |
| pipeline_tag: text-ranking | |
| base_model: Qwen/Qwen3-Reranker-8B | |
| datasets: | |
| - FIdo-AI/ua-squad | |
| tags: | |
| - reranker | |
| - text-ranking | |
| - qwen3 | |
| # Qwen3-Reranker-8B-squad | |
| Fine-tuned from base model: [`Qwen/Qwen3-Reranker-8B`](https://huggingface.co/Qwen/Qwen3-Reranker-8B) | |
| Datasets used: | |
| - [`FIdo-AI/ua-squad`](https://huggingface.co/datasets/FIdo-AI/ua-squad) | |
| Intended for Ukrainian QA / retrieval tasks. | |