Instructions to use ApacheOne/expimodel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ApacheOne/expimodel with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ApacheOne/expimodel", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "source_model_dir": "/content/ApacheOne-expimodel/merged-load-v3", | |
| "source_key_count": 759, | |
| "loaded_key_count": 759, | |
| "missing_key_count": 0, | |
| "extra_key_count": 0, | |
| "modelopt_version": "0.43.0", | |
| "torch_version": "2.10.0+cu128", | |
| "torch_dtype_load": "bfloat16", | |
| "weight_only_nvfp4": true, | |
| "quantize_lm_head": false, | |
| "skip_visual_mlp_linears": true, | |
| "disabled_quantizer_count": 165, | |
| "failed_disable_quantizer_count": 0, | |
| "patched_amax_count": 320, | |
| "skipped_amax_count": 0, | |
| "single_safetensors_out": "/content/HiDream-O1-Image-Dev-full-NVFP4-modelopt-v4.safetensors" | |
| } |