CodeV is a 7-billion-parameter vision-language model fine-tuned based on Qwen2.5-VL-7B-Instruct. Through two-stage training of supervised fine-tuning (SFT) and reinforcement learning (RL) based on tool-aware policy optimization (TAPO), it aims to achieve reliable and interpretable visual reasoning. It represents visual tools as executable Python code and ensures the consistency between tool usage and question evidence through a reward mechanism, solving the problem of irrelevant tool invocation under high accuracy.

MultimodalTransformersMultiple Languages

Olmo 3 is a series of language models developed by the Allen Institute for AI, including two scales of 7B and 32B, with two variants: instructional and reflective. This model performs excellently in long-chain thinking and can effectively improve the performance of reasoning tasks such as mathematics and coding. It adopts a multi-stage training method, including supervised fine-tuning, direct preference optimization, and reinforcement learning with verifiable rewards.

Natural Language ProcessingTransformersEnglish

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

This is a 32B parameter reward model developed by NVIDIA based on the Qwen3 architecture. It is specifically used for reward scoring and principle alignment in reinforcement learning, helping to train AI systems that are safer and more in line with human values.

Natural Language ProcessingGguf

SimPO is a simple preference optimization method that eliminates the need for reference rewards, aiming to enhance model performance by simplifying the preference optimization process.

Natural Language ProcessingTransformers

InternLM-Math is a state-of-the-art bilingual open-source large language model for mathematical reasoning developed by the Shanghai AI Laboratory. It performs excellently in mathematical reasoning tasks, supports the solution and proof of various mathematical problems, can also be used as a reward model, and has practical functions such as data enhancement and code explanation.

Natural Language ProcessingGgufMultiple Languages