Minh-Thien Nguyen
minhnguyent546
AI & ML interests
Research interests: Embeddings Models, Image-Text retrieval for Vietnamese, Optimal transport, RAG, and Image classification. Some pet projects on distributed training, training model on TPU, RAG for complex document multiple-choice QA.
Recent Activity
updated a collection about 16 hours ago
e2026 updated a collection about 21 hours ago
e2026 updated a dataset 2 days ago
minhnguyent546/EXACT-2026-CoTuOrganizations
cotu-legal-retriever is a family of models optimized for Vietnamese legal retrieval tasks.
-
minhnguyent546/cotu-legal-retriever-Octen-Embedding-4B-stage1
Sentence Similarity • 4B • Updated • 41 -
minhnguyent546/cotu-legal-retriever-Qwen3-Embedding-4B-stage1
Sentence Similarity • 4B • Updated • 53 -
minhnguyent546/cotu-legal-retriever-Qwen3-Embedding-8B-stage1
Sentence Similarity • 8B • Updated • 24 -
minhnguyent546/KaLM-Embedding-Gemma3-12B-2511-tokenizer-for-transformers-v5
Updated
cotu-legal-retriever is a family of models optimized for Vietnamese legal retrieval tasks.
-
minhnguyent546/cotu-legal-retriever-Octen-Embedding-4B-stage1
Sentence Similarity • 4B • Updated • 41 -
minhnguyent546/cotu-legal-retriever-Qwen3-Embedding-4B-stage1
Sentence Similarity • 4B • Updated • 53 -
minhnguyent546/cotu-legal-retriever-Qwen3-Embedding-8B-stage1
Sentence Similarity • 8B • Updated • 24 -
minhnguyent546/KaLM-Embedding-Gemma3-12B-2511-tokenizer-for-transformers-v5
Updated
models 25
minhnguyent546/noname002-jina-embeddings-v5-text-nano-retrieval-df-3fre-culturalY-vi-stage1
Sentence Similarity • 0.2B • Updated • 29
minhnguyent546/cotu-legal-retriever-Octen-Embedding-8B-stage1
Sentence Similarity • 8B • Updated • 22
minhnguyent546/cotu-legal-retriever-KaLM-Embedding-Gemma3-12B-2511-stage1
Sentence Similarity • 12B • Updated • 27
minhnguyent546/KaLM-Embedding-Gemma3-12B-2511-tokenizer-for-transformers-v5
Updated
minhnguyent546/cotu-legal-retriever-Qwen3-Embedding-8B-stage1
Sentence Similarity • 8B • Updated • 24
minhnguyent546/cotu-legal-retriever-Qwen3-Embedding-4B-stage1
Sentence Similarity • 4B • Updated • 53
minhnguyent546/cotu-legal-retriever-Octen-Embedding-4B-stage1
Sentence Similarity • 4B • Updated • 41
minhnguyent546/viclip-ot-mscoco-checkpoints
Updated
minhnguyent546/fastvilr
Updated
minhnguyent546/SEA-LION-ModernBERT-Embedding-600M
0.6B • Updated • 6
datasets 37
minhnguyent546/EXACT-2026-CoTu
Viewer • Updated • 2.8k • 38
minhnguyent546/wheelhouse
Updated • 51
minhnguyent546/viclip-ot-datasets
Updated • 13 • 1
minhnguyent546/flash-attn-v2.8.3-glibc-2.31
Updated • 123
minhnguyent546/LaVie-dataset
Preview • Updated • 1
minhnguyent546/CulturaY-vi
Viewer • Updated • 7.74M • 772
minhnguyent546/mc4-vi
Viewer • Updated • 78.6k • 65
minhnguyent546/Vi-VLEval-dataset-old
Preview • Updated • 30
minhnguyent546/datacomp_large_vie
Viewer • Updated • 6.79M • 15
minhnguyent546/ClimbMix-6BT
Updated • 472