Aleksei Dorkin PRO
adorkin
AI & ML interests
Computational Linguistics
Recent Activity
upvoted an article about 13 hours ago
BenchMIRT: What are LLM benchmarks actually measuring? updated a model 1 day ago
tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125 updated a model 1 day ago
tartuNLP/Llama-3.1-EstLLM-70B-Instruct-0826Organizations
Multilingual Text Embedding Models
-
tencent/KaLM-Embedding-Gemma3-12B-2511
Sentence Similarity • 12B • Updated • 17.8k • 102 -
nvidia/llama-embed-nemotron-8b
Feature Extraction • 8B • Updated • 419k • 170 -
Qwen/Qwen3-Embedding-8B
Feature Extraction • 8B • Updated • 2.35M • • 792 -
Qwen/Qwen3-Embedding-4B
Feature Extraction • 4B • Updated • 3.22M • • 317
Multilingual Text Encoders
Multilingual Text Embedding Models
-
tencent/KaLM-Embedding-Gemma3-12B-2511
Sentence Similarity • 12B • Updated • 17.8k • 102 -
nvidia/llama-embed-nemotron-8b
Feature Extraction • 8B • Updated • 419k • 170 -
Qwen/Qwen3-Embedding-8B
Feature Extraction • 8B • Updated • 2.35M • • 792 -
Qwen/Qwen3-Embedding-4B
Feature Extraction • 4B • Updated • 3.22M • • 317
spaces 6
Running
Agents
1
NLI Zero Shot Classification
🔍
Zero-shot classification based on natural language inference
Running
Agents
2
GliLem
🤓
Lemmatization disambiguation for Estonian with GliNER
Sleeping
Agents
SigLIP2 + Clothes
🤔
Text-to-image clothing search using SigLIP2
Running
Agents
1
M-CLIP + Clothes
🦀
Text-to-image clothing search using multilingual CLIP
Sleeping
Agents
1
Tweet Emoji Predictor
🧐
Predict an emoji for your tweet (...your X?)
Runtime error
Agents
Sõnajaht Demo
🐠
Keeltevaheline pöördsõnastik
datasets 30
adorkin/replay-mix-10B
Viewer • Updated • 5.99M • 72
adorkin/olmocr_science_pdfs-software
Viewer • Updated • 734k • 119
adorkin/olmocr_science_pdfs-travel_and_tourism
Viewer • Updated • 350k • 25
adorkin/olmocr_science_pdfs-art_and_design
Viewer • Updated • 873k • 36
adorkin/olmocr_science_pdfs-history_and_geography
Viewer • Updated • 1.67M • 71
adorkin/olmocr_science_pdfs-literature
Viewer • Updated • 1.85M • 291
adorkin/olmocr_science_pdfs-software_development
Viewer • Updated • 2.21M • 21
adorkin/olmocr_science_pdfs-games
Viewer • Updated • 157k • 34
adorkin/scientific-summaries-pubmed-open-access
Viewer • Updated • 270k • 48
adorkin/nemotron-code-student-teacher-10M
Viewer • Updated • 10M • 421