Loading
Tem um workflow do ComfyUI? Gere uma documentação legível direto no navegador.Torne um workflow legível.Experimentar agora ↗
This is a NVIDIA Model Optimizer W4A8 post-training quantized checkpoint of:
Fonte do modelo
Descrição da fonte
This is a NVIDIA Model Optimizer W4A8 post-training quantized checkpoint of:
laion/CLIP-ViT-L-14-laion2B-s32B-b82K
The checkpoint was produced with NVIDIA ModelOpt using W4A8/AWQ-style post-training quantization. Patch embedding quantization was disabled because it gave better retrieval quality in this experiment.
Evaluation was run on COCO val retrieval with 5,000 images.
Fontes
1 fonteVerificado 17 de set.
Artefatos de modelo
1 artefatoTrechos de fonte
2 trechos| Metric | W4A8 | Delta vs FP16 |
|---|
| image-to-text R@1 | 0.6168 | -0.0078 |
| image-to-text R@5 | 0.8372 | -0.0048 |
| image-to-text R@10 | 0.8992 | -0.0068 |
| text-to-image R@1 | 0.4417 | -0.0173 |
| text-to-image R@5 | 0.6959 | -0.0108 |
| text-to-image R@10 | 0.7867 | -0.0060 |
This is a ModelOpt checkpoint and includes modelopt_state.pth.
To restore it correctly, use NVIDIA ModelOpt with Hugging Face checkpointing enabled.
This experiment measures retrieval quality, not production latency. For real acceleration claims, benchmark an optimized deployment runtime separately.
Base model: laion/CLIP-ViT-L-14-laion2B-s32B-b82K
--- license: mit base_model: laion/CLIP-ViT-L-14-laion2B-s32B-b82K library_name: transformers tags: - clip - vision-language - modelopt - quantization - w4a8 - awq - coco --- # CLIP ViT-L/14 W4A8 ModelOpt Quantization This is a NVIDIA Model Optimizer W4A8 post-training quantized checkpoint of: `laion/CLIP-ViT-L-14-laion2B-s32B-b82K` The checkpoint was produced with NVIDIA ModelOpt using W4A8/AWQ-style post-training quantization. Patch embedding quantization was disabled because it gave better retrieval quality in this experiment. ## Evaluation Evaluation was run on COCO val retrieval with 5,000 images. | Metric | W4A8 | Delta vs FP16 | |---|---:|---:| | image-to-text R@1 | 0.6168 | -0.0078 | | image-to-text R@5 | 0.8372 | -0.0048 | | image-to-text R@10 | 0.8992 | -0.0068 | | text-to-image R@1 | 0.4417 | -0.0173 | | text-to-image R@5 | 0.6959 | -0.0108 | | text-to-image R@10 | 0.7867 | -0.0060 | ## Notes This is a ModelOpt checkpoint and includes `modelopt_state.pth`. To restore it correctly, use NVIDIA ModelOpt with Hugging Face checkpointing enabled. This experiment measures retrieval quality, not production latency. For real acceleration claims, benchmark an optimized deployment runtime separately. ## Base model Base model: `laion/CLIP-ViT-L-14-laion2B-s32B-b82K`
Source context: 8 downloads · 0 likes · Pipeline zero-shot-image-classification · Library transformers · Repo herooooooooo/clip-vit-l-14-laion2b-coco-w4a8-modelopt
