Publish ModernBERT-CNN with concise usage, training details and own evaluation metrics
90316bb verified Download evaluation/modernbert.bertscore.json from AhmedSSabir/ModernBERT-CNN-Caption-Reranker: direct link, hf CLI and curl.
- Browser
- Download file 658 Bytes
-
https://huggingface.co/AhmedSSabir/ModernBERT-CNN-Caption-Reranker/resolve/main/evaluation/modernbert.bertscore.json
- Command line
-
hf download hf://AhmedSSabir/ModernBERT-CNN-Caption-Reranker/evaluation/modernbert.bertscore.json
-
curl -L -o modernbert.bertscore.json https://huggingface.co/AhmedSSabir/ModernBERT-CNN-Caption-Reranker/resolve/main/evaluation/modernbert.bertscore.json
658 Bytes
| { | |
| "predictions_sha256": "8add6269339d94f5abb0542bb64c304feb4584b01708ae8a945e14a1606ac234", | |
| "references_sha256": "14ebad0ef1a546782a6a77d533c413e8a46ae179d7476872da91edb03c67d38d", | |
| "bertscore_hash": "roberta-large_L17_no-idf_version=0.3.12(hug_trans=5.3.0)", | |
| "images": 5000, | |
| "metrics": { | |
| "precision": 0.9421024364829064, | |
| "recall": 0.9399086234927178, | |
| "f1": 0.9398203430771828 | |
| }, | |
| "protocol": "Raw captions, all available references (at least five), max over references, RoBERTa-large layer 17, no IDF, no rescaling, slow tokenizer", | |
| "packages": { | |
| "bert-score": "0.3.13", | |
| "transformers": "5.3.0", | |
| "torch": "2.6.0" | |
| } | |
| } | |