Compact multilingual embedding models with 8M and 25M active parameters, including pretrained checkpoints and retrieval-fine-tuned releases.
Yuichi Tateno PRO
hotchpotch
AI & ML interests
Information Retrieval with LLMs
Recent Activity
published a model about 12 hours ago
hotchpotch/bekko-embedding-v1-a25m-pt published a model about 12 hours ago
hotchpotch/bekko-embedding-v1-a8m-pt updated a collection about 12 hours ago
bekko-embedding-v1Organizations
OpenProvence is a fully open-source implementation of Provence-style reranker–pruner models. These models remove irrelevant context while simultaneous
-
Open Provence Demo
✂4Context pruning demo for context engineering and RAG
-
hotchpotch/open-provence-reranker-xsmall-v1
Text Ranking • 36.8M • Updated • 3.4k • 1 -
hotchpotch/open-provence-reranker-v1
Text Ranking • 0.1B • Updated • 29 -
hotchpotch/open-provence-reranker-v1-gte-modernbert-base
Text Ranking • 0.1B • Updated • 91 • 2
Compact multilingual embedding models with 8M and 25M active parameters, including pretrained checkpoints and retrieval-fine-tuned releases.
OpenProvence is a fully open-source implementation of Provence-style reranker–pruner models. These models remove irrelevant context while simultaneous
-
Open Provence Demo
✂4Context pruning demo for context engineering and RAG
-
hotchpotch/open-provence-reranker-xsmall-v1
Text Ranking • 36.8M • Updated • 3.4k • 1 -
hotchpotch/open-provence-reranker-v1
Text Ranking • 0.1B • Updated • 29 -
hotchpotch/open-provence-reranker-v1-gte-modernbert-base
Text Ranking • 0.1B • Updated • 91 • 2
spaces 6
Running
bekko-embedding-web
🚀
Compare semantic similarity of your text lines
Sleeping
Agents
4
Open Provence Demo
✂
Context pruning demo for context engineering and RAG
Sleeping
3
Japanese Splade Demo Streamlit
📉
Convert text to SPLADE token scores
Running
TokenViz: AutoTokenizer Visualization Tool
🔍
Visualize the results of AutoTokenizer
Build error
Secon Dev Site Search
🐨
Running
6
Wikipedia Japanese Rag Search
😻
Ask questions about Wikipedia articles in Japanese
models 54
hotchpotch/bekko-embedding-v1-a8m
Sentence Similarity • 0.1B • Updated • 195
hotchpotch/bekko-embedding-v1-a25m
Sentence Similarity • 0.1B • Updated • 128 • 1
hotchpotch/bekko-embedding-v1-a8m-pt
Sentence Similarity • 0.1B • Updated • 22 • 1
hotchpotch/bekko-embedding-v1-a25m-pt
Sentence Similarity • 0.1B • Updated • 18 • 1
hotchpotch/japanese-reranker-base-v2
Text Ranking • 0.1B • Updated • 2.29k • 8
hotchpotch/japanese-reranker-small-v2
Text Ranking • 70.2M • Updated • 1.35k • 3
hotchpotch/japanese-reranker-xsmall-v2
Text Ranking • 36.8M • Updated • 51k • 6
hotchpotch/japanese-reranker-tiny-v2
Text Ranking • 29.4M • Updated • 725 • 6
hotchpotch/query-crafter-multilingual
Text Generation • 2B • Updated • 11
hotchpotch/CAT-Translate-0.8b-mlx-q8
Text Generation • 0.2B • Updated • 12
datasets 67
hotchpotch/bekko-embedding-v1-unsupervised
Updated • 5.76k
hotchpotch/bekko-embedding-v1-hard-negatives
Viewer • Updated • 760k • 188
hotchpotch/wikipedia-synthetic-nli
Viewer • Updated • 5.81M • 110
hotchpotch/wikipedia-multilingual-ir-related-lead-pairs
Viewer • Updated • 34.1M • 5.5k
hotchpotch/wikipedia-multilingual-ir-related-paragraph-pairs
Viewer • Updated • 19.6M • 614
hotchpotch/wikipedia-multilingual-ir-pairs
Viewer • Updated • 95.8M • 943
hotchpotch/wikipedia-multilingual-synthetic-ir-query
Viewer • Updated • 73.4M • 4.4k
hotchpotch/nllb-english-bitext-hq
Viewer • Updated • 280M • 2.38k
hotchpotch/multilingual-cc-news-ir-related-paragraph-pairs
Viewer • Updated • 68M • 1.72k
hotchpotch/wikipedia-english-ir-simulated-search-queries
Viewer • Updated • 29.4M • 391