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

Stable Diffusion v2-1-base is a diffusion model for text-to-image generation, which has been fine-tuned with an additional 220k steps based on v2-base. This model can generate and modify images according to text prompts, support multiple resolution outputs, and is suitable for various fields such as artistic creation and educational research.

Computer VisionDiffusers

A lightweight medical fine-tuned model based on Arcee's AFM-4.5B, optimized using a three-stage training method (SFT→DPO→GRPO-CoT), specifically designed for medical education and research scenarios.

Natural Language ProcessingTransformersMultiple Languages

Gemma-3 ActuaryEnough2 is an AI model specifically designed for the actuarial field. It is fine-tuned based on over 11,000 actuarial Q&A pairs and can transform simple insurance questions into rigorous actuarial professional language. This model supports ActuaryEnough and is released in an open-source form for education and research purposes.

Natural Language ProcessingTransformersEnglish

MedScholar-1.5B is a compact medical Q&A model based on the Qwen2.5-1.5B-Instruct architecture, fine-tuned using 1 million samples from the MIRIAD-4.4M dataset. This model is specifically designed for clinical knowledge research and educational exploration, trained using the Unsloth framework and QLoRA, and strictly used for non-clinical academic purposes.

Natural Language ProcessingTransformersEnglish

OLMo 2 1B RLVR 1 April 2025 is a post-trained variant based on the allenai/OLMo-2-0425-1B-DPO model, which has been fine-tuned on multiple specific datasets. This model has demonstrated good performance in multiple tasks such as mathematical reasoning, code generation, and instruction following. It is a large language model with 1B parameters designed specifically for research and educational purposes.

Natural Language ProcessingTransformersEnglish

OLMo-2-1124-7B-SFT is a version that undergoes supervised fine-tuning based on the OLMo 2 7B model. It is trained on the Tülu 3 dataset and performs excellently on various tasks, suitable for research and education fields.

Natural Language ProcessingTransformersEnglish

Teuken 7B-base-v0.6 is a multilingual large language model with 7 billion parameters, pre-trained on 6 trillion tokens in the OpenGPT-X research project. This model is designed for private, non-commercial, research, and educational purposes in the 24 official languages of the EU, and can provide stable performance in multilingual environments.

Natural Language ProcessingTransformersMultiple Languages

The GGUF version of the StableDiffusion 3.5 medium model is a powerful diffusion model for text-to-image generation, with significant improvements in image quality, typesetting effects, complex prompt understanding, and resource efficiency. This model uses an improved multimodal diffusion transformer architecture and supports multiple text encoders, making it suitable for scenarios such as art creation, educational tools, and generative model research.

MultimodalDiffusersEnglish

GPT-2 Mini is a lightweight variant of the GPT-2 model with only 39 million parameters. This model is pre-trained on a subset of the OpenWebText dataset and is specifically designed for research and educational scenarios. It can quickly conduct text generation experiments in environments with limited resources.

Natural Language ProcessingTransformersEnglish

A programming assistant language model fine-tuned based on StarCoder, with 16 billion parameters, supports English, suitable for the field of educational research

Natural Language ProcessingTransformersMultiple Languages

A BLOOM language model with Traditional Chinese enhancement, jointly developed by MediaTek Research, Academia Sinica, and the National Academy for Educational Research

Natural Language ProcessingTransformersChinese