| --- |
| datasets: |
| - tatsu-lab/alpaca |
| base_model: |
| - zai-org/GLM-OCR |
| pipeline_tag: image-text-to-text |
| --- |
| ## Using Hardware |
|
|
| - CPU: AMD Ryzen Threadripper PRO 7995WX |
| - MB: GIGABYTE AI TOP TRX50 |
| - GPU: RTX 5090*1 |
| - RAM: RDIMM DDR5 5600 128GB*2 |
|
|
| ## Using Software |
|
|
| - CUDA version: 13.0 |
| - CUDA driver version: 580.95.05 |
| - pyTorch: 2.10.0+cu130 |
| - transformers: 5.10.1 |
| - llmcompressor: 0.12.0 |
| - vllm: 0.24.0 |
|
|
| ## Backbone Model |
|
|
| [Qwen/Qwen3.5-9B](https://huggingface.co/zai-org/GLM-OCR) |
|
|
| ## Using Dataset |
|
|
| [tatsu-lab/alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca) convert as chat template. |
|
|
|
|
| ## Compare |
|
|
| | -- | origin model(BF16) | Quantization(This Model) | |
| | :--- | :---: | ---: | |
| | Leaderboard_GPQA | 0.2424 | 0.2525 | |
| | VRAM Usage | 2.21 GiB | 1.41 GiB | |
