Hunyuan-MT-7B is a 7B parameter translation model launched by Tencent, supporting mutual translation of 33 languages, including 5 ethnic minority languages in China. This model performed excellently in the WMT25 competition, winning the first place in 30 out of 31 language categories, and proposed a complete translation model training framework from pre-training to integrated optimization.

Natural Language ProcessingTransformersMultiple Languages

The Hunyuan translation model is an advanced machine translation system developed by Tencent, including the translation model Hunyuan-MT-7B and the integrated model Hunyuan-MT-Chimera. This model supports mutual translation of 33 languages, including mainstream languages such as Chinese, English, and French, as well as five ethnic minority languages in China, and performed excellently in the WMT25 competition.

Natural Language ProcessingTransformers

This is the GGUF quantized version of the Qwen3-Code-Reasoning-4B model, specifically optimized for competition programming and code reasoning tasks. The model is trained on a high-quality code reasoning dataset, enhancing its ability to solve complex programming problems through detailed reasoning.

Natural Language ProcessingGgufEnglish

This is the GGUF quantized version of the GPT-OSS-Code-Reasoning-20B model, optimized for efficient reasoning and reducing memory requirements. This model is specifically fine-tuned for competition programming and algorithm reasoning tasks, capable of generating Python/C++ solutions and reasoning processes.

Natural Language ProcessingGgufEnglish

Kimina-Prover-Distill-0.6B is a theorem proving model developed by Project Numina and the Kimi team, focusing on the ability to solve competition-style problems in Lean 4. It is a distilled version of the Kimina-Prover-72B model, achieving an accuracy of 68.85% on MiniF2F-test.

Natural Language ProcessingTransformersEnglish

A theorem proving model developed by the Project Numina and Kimi teams, focusing on the ability to solve competition-style problems in Lean 4.

Scientific ComputingTransformersEnglish

A theorem proving model developed by the Numina project and the Kimi team, focusing on improving the ability to solve competition-style problems in Lean 4.

Natural Language ProcessingTransformersEnglish

Kimina-Prover-Distill-8B is a theorem proving model developed by the Project Numina and Kimi teams, focusing on the ability to solve competition-style problems in Lean 4.

Natural Language ProcessingTransformersEnglish

M1 is a 3B parameter scale model based on the Mamba hybrid architecture, focusing on mathematical reasoning tasks and performing excellently in multiple mathematical competition benchmark tests.

Natural Language ProcessingTransformers

A mathematical reasoning model fine-tuned based on Qwen2.5-14B, achieving first place in the AIMO-2 Kaggle competition

Natural Language ProcessingTransformersEnglish

Light-R1-32B is a math competition-specific model trained based on Qwen2.5-32B-Instruct, achieving performance surpassing DeepSeek-R1-Distill through curriculum-style SFT and DPO techniques, with a training cost of only $1000.

Natural Language ProcessingTransformers

This model is specifically fine-tuned for SemEval 2025 Task3: Mu-SHROOM competition to identify hallucinated text segments in large language model outputs.

Natural Language ProcessingTransformers

ALMA-13B-R is an advanced translation model based on large language models, fine-tuned using Contrastive Preference Optimization (CPO), capable of matching or even surpassing GPT-4 or WMT competition winners.

Natural Language ProcessingTransformers

A text-to-image model based on Stable Diffusion 1.5, designed for the 'Weekly Image' competition on Discord, aiming to express emotions and stories through art.

Computer VisionDiffusersEnglish

A toxic comment classification tool based on PyTorch Lightning and Hugging Face Transformers, providing three models trained for Jigsaw competitions

Natural Language ProcessingJax

A toxicity classification model fine-tuned based on RoBERTa-large, trained on the Jigsaw competition dataset for identifying toxic content in English text.

Natural Language ProcessingTransformersEnglish

Korean dialogue summarization model based on BART architecture, trained by the 'Alaggung Dalaggung' team in the 2021 Hunminjeongeum Korean Speech & Natural Language AI Competition

Natural Language ProcessingTransformersKorean

A Korean dialogue summarization model based on the BART pre-trained model, trained with R3F technology, participating in the 2021 Hunminjeongeum Korean Speech & Natural Language AI Competition

Natural Language ProcessingTransformersKorean

This model is a dense retrieval model based on the TCT-ColBERT-V2 architecture, fine-tuned for the MS MARCO-V2 passage ranking task and used for TREC DL 2021 competition submissions.

Natural Language ProcessingTransformers

A Luganda automatic speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, specifically developed for the Mozilla Competition

Audio ProcessingTransformersOther