Article
Yuichi Tateno PRO
hotchpotch
AI & ML interests
Information Retrieval with LLMs
Recent Activity
new activity about 16 hours ago
hotchpotch/s1mb-result:Add Liquid AI d1:free generalization results new activity about 18 hours ago
hotchpotch/s1mb-result:Add 16 complete English model evaluations with inference conditions liked a model 1 day ago
openjev/openjevOrganizations
Articles 5
Article
S1MB: comparing System One Decision Models across 100+ benchmarks
Compact multilingual embedding models with 8M and 25M active parameters, including pretrained checkpoints and retrieval-fine-tuned releases.
-
hotchpotch/bekko-embedding-v1-a8m
Sentence Similarity • 0.1B • Updated • 8.63k • • 19 -
hotchpotch/bekko-embedding-v1-a25m
Sentence Similarity • 0.1B • Updated • 34.6k • • 31 -
bekko-embedding-web
🚀4Run ultra-compact multilingual embeddings in your browser.
-
Bekko Embedding: Parameter-Efficient Multilingual Retrieval with Ultra-Compact Encoders
Paper • 2607.25180 • Published • 4
Ultra small system one models
Compact multilingual embedding models with 8M and 25M active parameters, including pretrained checkpoints and retrieval-fine-tuned releases.
-
hotchpotch/bekko-embedding-v1-a8m
Sentence Similarity • 0.1B • Updated • 8.63k • • 19 -
hotchpotch/bekko-embedding-v1-a25m
Sentence Similarity • 0.1B • Updated • 34.6k • • 31 -
bekko-embedding-web
🚀4Run ultra-compact multilingual embeddings in your browser.
-
Bekko Embedding: Parameter-Efficient Multilingual Retrieval with Ultra-Compact Encoders
Paper • 2607.25180 • Published • 4
spaces 8
Running
1
S1MB Leaderboard
📊
Compare System One models across 100+ specialized benchmarks
Running
4
Ultra-small System One Models in Your Browser
🐂
Answer Yes/No questions, choose options, and score inputs.
Running
4
bekko-embedding-web
🚀
Run ultra-compact multilingual embeddings in your browser.
Running
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
Sleeping
TokenViz: AutoTokenizer Visualization Tool
🔍
Visualize the results of AutoTokenizer
models 59
hotchpotch/bekko-system-one-v0-400m
Updated • 3
hotchpotch/bekko-system-one-v0-68m
Updated • 1
hotchpotch/bekko-system-one-v0-17m
Updated • 4
hotchpotch/bekko-embedding-v1-a25m-GGUF
Feature Extraction • 0.1B • Updated • 219
hotchpotch/bekko-embedding-v1-a8m-GGUF
Feature Extraction • 0.1B • Updated • 153
hotchpotch/bekko-embedding-v1-a25m
Sentence Similarity • 0.1B • Updated • 34.6k • • 31
hotchpotch/bekko-embedding-v1-a8m
Sentence Similarity • 0.1B • Updated • 8.63k • • 19
hotchpotch/bekko-embedding-v1-a8m-pt
Sentence Similarity • 0.1B • Updated • 116 • 2
hotchpotch/bekko-embedding-v1-a25m-pt
Sentence Similarity • 0.1B • Updated • 106 • 1
hotchpotch/japanese-reranker-base-v2
Text Ranking • 0.1B • Updated • 4.7k • 8
datasets 71
hotchpotch/s1mb-result
Updated • 237
hotchpotch/bekko-system-one-dataset-v0
Viewer • Updated • 6.61M • 192 • 1
hotchpotch/s1mb-dataset
Viewer • Updated • 14k • 1.57k
hotchpotch/bekko-embedding-v1-unsupervised
Updated • 11.5k • 4
hotchpotch/bekko-embedding-hard-negatives
Updated • 31 • 1
hotchpotch/bekko-embedding-v1-hard-negatives
Viewer • Updated • 760k • 1.41k • 3
hotchpotch/wikipedia-synthetic-nli
Viewer • Updated • 5.81M • 12
hotchpotch/wikipedia-multilingual-ir-related-lead-pairs
Viewer • Updated • 34.1M • 70
hotchpotch/wikipedia-multilingual-ir-related-paragraph-pairs
Viewer • Updated • 19.6M • 127
hotchpotch/wikipedia-multilingual-ir-pairs
Viewer • Updated • 95.8M • 920