Translation‑table document expansion The count-based translation table that can enrich the inverted index for full-text search Collection by mirth 5 days ago 1 mirth/msmarco-expansion-tables Updated 5 days ago • 1
CASS: Arabic Semantic Similarity, fine-tuned models Paper: https://doi.org/10.1007/s10579-026-09948-2 Dataset: https://doi.org/10.5281/zenodo.21726079 Collection by MJ92 5 days ago 1 MJ92/AceGPT-v2-8B-Chat_finetuned_250_cass Text Generation • 8B • Updated Feb 19, 2025 • 16 MJ92/AceGPT-13B-chat_finetuned_564 Text Generation • 13B • Updated Oct 15, 2024 • 16 MJ92/AceGPT-7B_finetuned_500 Updated Nov 21, 2024 MJ92/AceGPT-v2-8B-Chat_finetuned_1000_cass Text Generation • 8B • Updated Jul 15, 2025 • 10
DASH-OPD Model Collection Six Qwen3-based student models trained with DASH-OPD across WebShop, ALFWorld, and ScienceWorld, available in 1.7B and 4B sizes. Collection by Lucian1115 5 days ago 1 Lucian1115/DASH-OPD-Qwen3-1.7B-WebShop 2B • Updated 5 days ago • 14 • 2 Lucian1115/DASH-OPD-Qwen3-4B-WebShop 4B • Updated 5 days ago • 11 • 2 Lucian1115/DASH-OPD-Qwen3-1.7B-ALFWorld 2B • Updated 5 days ago • 14 • 1 Lucian1115/DASH-OPD-Qwen3-4B-ALFWorld 4B • Updated 5 days ago • 17 • 2
BuzzASR: 102 Monolingual ASR Models Language-specialized Whisper-large-v3 fine-tunes, one per FLEURS language. Findings of EMNLP 2026. arxiv.org/abs/2609.09554 Collection by vamsin07 5 days ago 1 BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models Paper • 2609.09554 • Published 10 days ago • 1 BuzzASR/afrikaans Automatic Speech Recognition • 2B • Updated 11 days ago • 12 BuzzASR/amharic Automatic Speech Recognition • 2B • Updated 11 days ago • 52 BuzzASR/arabic Automatic Speech Recognition • 2B • Updated 11 days ago • 27
BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models Paper • 2609.09554 • Published 10 days ago • 1
Parrot Coder 🦜 Collection by InserloftResearch 5 days ago 1 InserloftResearch/Parrot-Coder Text Generation • 0.3B • Updated 6 days ago • 422
ACÁCIA PERFUMARIA Campo Grande - MS https://www.instagram.com/acaciaperfumaria/ Collection by Shoyuo 5 days ago 1
Badr: Arabic Fiqh Retrieval Resources for answer-bearing Arabic fiqh retrieval, including the Badr model, dataset, and paper. Collection by somayaeltanbouly 3 days ago 1 What Makes a Good Fiqh Retriever? Answer Retrieval for Arabic Islamic Jurisprudence Paper • 2608.20246 • Published about 1 month ago somayaeltanbouly/Badr_embedding_v0 Sentence Similarity • 0.1B • Updated 5 days ago somayaeltanbouly/Badr_fiqh_retrieval_triplets Viewer • Updated 5 days ago • 19.3k • 19
What Makes a Good Fiqh Retriever? Answer Retrieval for Arabic Islamic Jurisprudence Paper • 2608.20246 • Published about 1 month ago
Supernova tokenizer Supernova tokenizer collection v5 strong in all of them implement the complete different Moe Architecture Collection by Supernova11c 3 days ago 1 Supernova11c/Supernova-Nepali-Tokenizer Updated 3 days ago • 1 Supernova11c/Supernova-NepaliFast-V4 Updated 13 days ago • 1 Supernova11c/Supernova-NepaliFast-V5 Updated 1 day ago • 1 Supernova11c/Supernova-Nepali-Tokenizer-V3 Updated about 1 month ago • 1
Mailroom Corpus Family LLM-Mailroom evaluation corpus: mailroom-dataset v1/v9 + frozen v8 mailroom-corpus + the upstream source corpora it is drawn from. Collection by Lucius-Morningstar 5 days ago 1 Lucius-Morningstar/mailroom-dataset Viewer • Updated 5 days ago • 6.75k • 191 • 1 Lucius-Morningstar/mailroom-corpus Viewer • Updated 6 days ago • 4.14k • 527 • 1 Lucius-Morningstar/enron-correspondence-dedup Updated 20 days ago • 320 • 1 Lucius-Morningstar/mailroom-cuad-contracts-full Preview • Updated 26 days ago • 57
Computer Vision & Applied AI Projects Selected computer vision and applied AI projects covering object detection, real-world ML workflows, and end-to-end AI applications. Collection by Ibrahim276 6 days ago 1 Running on Zero Agents Currency Assistant 🦀 Detects and identifies Pakistani banknotes (RT-DETR Sleeping Agents YOLOv8_Object_Detection 🚀 Detect objects in your photos with bounding boxes
Translation‑table document expansion The count-based translation table that can enrich the inverted index for full-text search Collection by mirth 5 days ago 1 mirth/msmarco-expansion-tables Updated 5 days ago • 1
ACÁCIA PERFUMARIA Campo Grande - MS https://www.instagram.com/acaciaperfumaria/ Collection by Shoyuo 5 days ago 1
CASS: Arabic Semantic Similarity, fine-tuned models Paper: https://doi.org/10.1007/s10579-026-09948-2 Dataset: https://doi.org/10.5281/zenodo.21726079 Collection by MJ92 5 days ago 1 MJ92/AceGPT-v2-8B-Chat_finetuned_250_cass Text Generation • 8B • Updated Feb 19, 2025 • 16 MJ92/AceGPT-13B-chat_finetuned_564 Text Generation • 13B • Updated Oct 15, 2024 • 16 MJ92/AceGPT-7B_finetuned_500 Updated Nov 21, 2024 MJ92/AceGPT-v2-8B-Chat_finetuned_1000_cass Text Generation • 8B • Updated Jul 15, 2025 • 10
Badr: Arabic Fiqh Retrieval Resources for answer-bearing Arabic fiqh retrieval, including the Badr model, dataset, and paper. Collection by somayaeltanbouly 3 days ago 1 What Makes a Good Fiqh Retriever? Answer Retrieval for Arabic Islamic Jurisprudence Paper • 2608.20246 • Published about 1 month ago somayaeltanbouly/Badr_embedding_v0 Sentence Similarity • 0.1B • Updated 5 days ago somayaeltanbouly/Badr_fiqh_retrieval_triplets Viewer • Updated 5 days ago • 19.3k • 19
What Makes a Good Fiqh Retriever? Answer Retrieval for Arabic Islamic Jurisprudence Paper • 2608.20246 • Published about 1 month ago
DASH-OPD Model Collection Six Qwen3-based student models trained with DASH-OPD across WebShop, ALFWorld, and ScienceWorld, available in 1.7B and 4B sizes. Collection by Lucian1115 5 days ago 1 Lucian1115/DASH-OPD-Qwen3-1.7B-WebShop 2B • Updated 5 days ago • 14 • 2 Lucian1115/DASH-OPD-Qwen3-4B-WebShop 4B • Updated 5 days ago • 11 • 2 Lucian1115/DASH-OPD-Qwen3-1.7B-ALFWorld 2B • Updated 5 days ago • 14 • 1 Lucian1115/DASH-OPD-Qwen3-4B-ALFWorld 4B • Updated 5 days ago • 17 • 2
Supernova tokenizer Supernova tokenizer collection v5 strong in all of them implement the complete different Moe Architecture Collection by Supernova11c 3 days ago 1 Supernova11c/Supernova-Nepali-Tokenizer Updated 3 days ago • 1 Supernova11c/Supernova-NepaliFast-V4 Updated 13 days ago • 1 Supernova11c/Supernova-NepaliFast-V5 Updated 1 day ago • 1 Supernova11c/Supernova-Nepali-Tokenizer-V3 Updated about 1 month ago • 1
BuzzASR: 102 Monolingual ASR Models Language-specialized Whisper-large-v3 fine-tunes, one per FLEURS language. Findings of EMNLP 2026. arxiv.org/abs/2609.09554 Collection by vamsin07 5 days ago 1 BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models Paper • 2609.09554 • Published 10 days ago • 1 BuzzASR/afrikaans Automatic Speech Recognition • 2B • Updated 11 days ago • 12 BuzzASR/amharic Automatic Speech Recognition • 2B • Updated 11 days ago • 52 BuzzASR/arabic Automatic Speech Recognition • 2B • Updated 11 days ago • 27
BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models Paper • 2609.09554 • Published 10 days ago • 1
Mailroom Corpus Family LLM-Mailroom evaluation corpus: mailroom-dataset v1/v9 + frozen v8 mailroom-corpus + the upstream source corpora it is drawn from. Collection by Lucius-Morningstar 5 days ago 1 Lucius-Morningstar/mailroom-dataset Viewer • Updated 5 days ago • 6.75k • 191 • 1 Lucius-Morningstar/mailroom-corpus Viewer • Updated 6 days ago • 4.14k • 527 • 1 Lucius-Morningstar/enron-correspondence-dedup Updated 20 days ago • 320 • 1 Lucius-Morningstar/mailroom-cuad-contracts-full Preview • Updated 26 days ago • 57
Parrot Coder 🦜 Collection by InserloftResearch 5 days ago 1 InserloftResearch/Parrot-Coder Text Generation • 0.3B • Updated 6 days ago • 422
Computer Vision & Applied AI Projects Selected computer vision and applied AI projects covering object detection, real-world ML workflows, and end-to-end AI applications. Collection by Ibrahim276 6 days ago 1 Running on Zero Agents Currency Assistant 🦀 Detects and identifies Pakistani banknotes (RT-DETR Sleeping Agents YOLOv8_Object_Detection 🚀 Detect objects in your photos with bounding boxes