| unsloth | |
| # Sinhala MMLU Shared Task - Team QBitsLK | |
| # Verified install: pip install -r requirements.txt && python inference.py | |
| # | |
| # Inference needs ONE GPU with >= 20 GB of memory (the model is 16 GB in bf16). | |
| # Reference machine: 1x NVIDIA A40 48 GB, driver 595.91, CUDA 13.2, Python 3.12. | |
| torch>=2.6 | |
| transformers==5.5.0 | |
| tokenizers>=0.22.0,<=0.23.0 | |
| huggingface_hub>=1.5.0,<2.0 | |
| accelerate>=1.0 | |
| timm # Gemma 4 ships a multimodal processor; loading it requires timm | |
| numpy | |
| hf_transfer # faster weight download; optional | |