Olmo-3-7B-Think-DPO is a 7B parameter language model developed by the Allen Institute for AI. It has the ability of long-chain thinking and performs excellently in reasoning tasks such as mathematics and coding. This model has undergone multi-stage training including supervised fine-tuning, direct preference optimization, and reinforcement learning based on verifiable rewards, and is designed specifically for research and educational purposes.

Natural Language ProcessingTransformersEnglish

Gaperon-Young-1125-1B is a bilingual (French-English) language model with 1.5 billion parameters, developed by the ALMAnaCH team at the French National Institute for Research in Computer Science and Control (Inria Paris). The model is trained on approximately 3 trillion high-quality tokens, with a particular focus on language quality and general text generation ability rather than benchmark test optimization.

Natural Language ProcessingTransformersMultiple Languages

This is a 4-bit quantized large language model based on the MLX framework, developed by the Swiss Artificial Intelligence Research Institute. It supports multilingual text generation tasks and is released under the Apache-2.0 license.

Natural Language ProcessingMlxOther

Fanar-1-9B-Instruct is a powerful Arabic-English large language model developed by the Qatar Computing Research Institute (QCRI). It supports Modern Standard Arabic and multiple Arabic dialects, and is aligned with Islamic values and Arab culture.

Natural Language ProcessingTransformersMultiple Languages

EAGLE is a decoder causal language model with 3.1 billion parameters developed by the Electronics and Telecommunications Research Institute (ETRI) in South Korea, focusing on the STEM fields, especially mathematics and quantitative reasoning. This model has been pre-trained on 720 billion tokens and uses a LLaMA-compatible architecture. However, it is not a general-purpose language model and requires additional fine-tuning to be used in applications such as chatbots.

Natural Language ProcessingTransformersKorean

MindLLM 1.3B is a 1.3 billion-parameter Transformer model jointly developed by the Beijing Engineering Research Center of Massive Language Information Processing and Cloud Computing Applications and the Southeast Institute of Information Technology, Beijing Institute of Technology, supporting Chinese and English dialogue generation.

Natural Language ProcessingTransformersMultiple Languages

This is a biomedical named entity recognition model jointly developed by Bayer Pharmaceuticals and the Serbian Institute for Artificial Intelligence Research and Development. It supports zero-shot and few-shot learning and can recognize 26 categories of biomedical entities, including various types such as diseases, chemicals, and genes.

Natural Language ProcessingTransformersEnglish

This is a Chinese pretrained BERT model using whole word masking strategy, released by the Harbin Institute of Technology-iFLYTEK Joint Laboratory to accelerate Chinese natural language processing research.

Natural Language ProcessingJaxChinese