Instructions to use Reza2kn/sapiens2-normal-5b-INT4-G128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sapiens
How to use Reza2kn/sapiens2-normal-5b-INT4-G128 with sapiens:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- sapiens2
How to use Reza2kn/sapiens2-normal-5b-INT4-G128 with sapiens2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| { | |
| "input": "/home/rezo/sapiens2_quant/run/downloads/facebook__sapiens2-normal-5b/sapiens2_5b_normal.safetensors", | |
| "output": "/home/rezo/sapiens2_quant/run/artifacts/facebook__sapiens2-normal-5b-int4-g128.safetensors", | |
| "group_size": 128, | |
| "tensor_count": 976, | |
| "quantized_tensor_count": 346, | |
| "source_bytes": 21265433176, | |
| "artifact_bytes": 2748608552, | |
| "compression_ratio": 7.736799465506429, | |
| "max_tensor_mae": 0.004410343244671822, | |
| "repo": "facebook/sapiens2-normal-5b", | |
| "fidelity": { | |
| "global_floating_similarity_percent": 99.32280520366463, | |
| "min_large_tensor_cosine": 0.9857655763626099, | |
| "threshold": 0.9 | |
| } | |
| } | |