Downloads · 30 days
9
23% of all-time downloads
mariklolik/ecup-2026-qilowoq-soft-human-final
ecup-2026-qilowoq-soft-human-final is a text classification model from mariklolik. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
Exact continuation checkpoint behind ODS submission qilowoq-soft-global-final-12c515e5.zip.
Downloads · 30 days
9
23% of all-time downloads
All-time downloads
40
Public
Parameters
375M
1.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.5 GB · 100%
From the Hugging Face model README
Exact continuation checkpoint behind ODS submission qilowoq-soft-global-final-12c515e5.zip.
0.47069991672790107Success12c515e5112dd526d227cfb62dc3764a27a67d0c0ad4cd841121ba236c1c5e9eeae1e3af1734e4e44ea5d438656dd93126b06af258a36605de99928e7cbf263dBase checkpoint: qilowoq/bge-reranker-v2-m3-en-ru at revision 0ca0a6a717ffbe01e25c6e8e33bad7982d938930.
The model is a sequence-classification cross-encoder over a canonicalized pair of product texts. Product text contains category, title, and normalized attributes. Item IDs are used only to make pair orientation deterministic and never enter model text.
Training has two stages:
Both stages use batch size 64, learning rate 4e-6, BF16 autocast, FP32 logits/loss, AdamW, global positive weighting, category weighting, gradient clipping, deterministic seed 42, and alternating pair-swap augmentation.
The checkpoint is saved as FP32 safetensors and reloaded before packaging. training-provenance.json, reranker-spec.json, and model-manifest.json bind every source and training artifact to SHA-256.
The GitHub repository and this model repository are private team assets.