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

Nanbeige 4-3B-Thinking-2511 is the latest enhanced version of the Nanbeige series. Through advanced distillation technology and reinforcement learning optimization, it achieves powerful reasoning ability within a compact 3B parameter scale. This model has achieved state-of-the-art (SOTA) results among models with less than 32B parameters in benchmark tests such as Arena-Hard-V2 and BFCL-V4.

Natural Language ProcessingTransformersMultiple 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

Olmo-3-32B-Think-DPO is a 32B parameter language model developed by Allen AI. It is trained using Direct Preference Optimization (DPO) and has the ability of long-chain thinking reasoning. It performs excellently in complex reasoning tasks such as mathematics and coding.

Natural Language ProcessingTransformersEnglish

This is a mixture-of-experts model based on Qwen3-Coder-30B-A3B-Instruct, with 54 billion parameters and a context length of 1 million. The model has powerful programming capabilities and general scenario processing capabilities through three-step merging and Brainstorm 40X optimization. It is especially integrated with a thinking module, which can perform in-depth reasoning before answering.

Natural Language ProcessingTransformersMultiple Languages

MedGemma-GRPO is a fine-tuned version of the MEDGemma model, specifically designed for clinical case reasoning tasks. This model combines supervised fine-tuning (SFT) and group relative policy optimization (GRPO) to guide the model to follow logical diagnostic paths. It is trained on a synthetic medical case dataset and is particularly suitable for diagnostic reasoning of complex cardiovascular, thrombotic, and autoimmune diseases.

Natural Language ProcessingTransformersEnglish

DeepSeek-R1-0528 is a minor version upgrade of the DeepSeek R1 model. It significantly improves the reasoning ability through increased computing resources and algorithm optimization, and performs excellently in multiple benchmark evaluations such as mathematics, programming, and general logic.

Natural Language ProcessingTransformers

The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 significantly enhanced its deep reasoning and inference capabilities by increasing computational resource investment and introducing algorithmic optimization mechanisms during the post-training phase.

Natural Language ProcessingTransformers

OpenVLThinker-7B is a vision-language reasoning model specifically designed for multimodal tasks, with particular optimization for solving visual mathematical problems.

MultimodalTransformers

R1-VL-2B is a vision-language reasoning model trained through Stepwise Group Relative Policy Optimization (StepGRPO), optimized based on Qwen2-VL-2B-Instruct.

MultimodalTransformers

Gemma-3-4b Reasoning is a Transformer-based language model fine-tuned using the GRPO method, specializing in reasoning task optimization.

Natural Language ProcessingTransformersEnglish

A medical chain-of-thought reasoning model fine-tuned from DeepSeek-R1-Distill-Llama-8B, enhanced with QLoRA quantization and Unsloth optimization for medical reasoning.

Natural Language ProcessingSafetensors

Phi-4-mini-instruct is a lightweight open-source model built on synthetic data and curated public websites, focusing on high-quality data with strong reasoning capabilities. It supports a 128K token context length and is enhanced through supervised fine-tuning and direct preference optimization to ensure precise instruction following and safety.

Natural Language ProcessingTransformersMultiple Languages

Pensez is a bilingual French-English reasoning model that maximizes efficiency by significantly reducing training data. This model is built on Qwen 2.5 Instruct 7B and focuses on daily reasoning tasks and scientific problems. It uses optimization strategies such as concise reasoning and extended reasoning to improve performance.

Natural Language ProcessingTransformersMultiple Languages

LLM Compiler is an advanced LLM based on Code Llama, specifically designed for code optimization and compiler reasoning tasks

Natural Language ProcessingTransformers

An advanced large language model for compiler optimization developed by Meta, built upon Code Llama, specializing in code optimization and compiler reasoning tasks.

Natural Language ProcessingTransformers

Llama-medx_v3.2 is a large language model specifically fine-tuned for the medical field, developed based on the Meta-Llama-3.1-8B architecture. It is trained using supervised fine-tuning (SFT) and odds ratio preference optimization (ORPO) techniques, accurately mastering medical terminology and clinical reasoning capabilities.

Natural Language ProcessingTransformers

Kunoichi-DPO-7B is a model fine-tuned using Intel's Orca data for direct preference optimization (DPO) on the Alpaca template based on the Kunoichi-7B model. It is mainly targeted at general scenarios and has stronger reasoning and instruction-following abilities.

Natural Language ProcessingTransformers

Neural-Chat-v3-3 is a 7-billion-parameter large language model developed by Intel based on the Mistral-7B architecture, focusing on mathematical reasoning and text generation tasks. The model is fine-tuned on the MetaMathQA dataset and aligned using Direct Performance Optimization (DPO) method.

Natural Language ProcessingTransformers