Clip Vit L 14 Laion2b Coco W4a8 Modelopt

--- 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