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

This model is an MLX format conversion version of the Ministral-3-3B-Instruct-2512 instruction fine-tuning model released by Mistral AI. It is a large language model with a parameter scale of 3B, specifically optimized for following instructions and dialogue tasks, and supports multiple languages. The MLX format enables it to run efficiently on Apple Silicon devices.

Natural Language ProcessingMlxMultiple Languages

Zenyx_114M-Tiny-Edu-Instruct is an experimental small instruction fine-tuned language model with approximately 114 million parameters. It is built on the TinyEdu-50M base model, pre-trained on the FineWeb-Edu dataset, and fine-tuned on a mixed dataset of OpenHermes-2.5 and CodeFeedback-Filtered. This model aims to explore the limits of instruction fine-tuning under a minimal architecture and verify that the loss converges to approximately 1.04.

Natural Language ProcessingPytorchEnglish

Olmo-3-7B-Instruct-AIO-GGUF is a GGUF quantized version based on the Olmo-3-7B-Instruct model developed by the Allen Institute for AI. This is an autoregressive language model with 7 billion parameters, trained on datasets such as Tulu 2 and UltraFeedback through supervised fine-tuning and direct preference optimization, and performs excellently in question-answering and instruction following.

Natural Language ProcessingTransformersEnglish

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

SDXL-Deepfake-Detector is a tool for accurately detecting AI-generated faces. It focuses on maintaining the authenticity of the digital world and provides a privacy-protected and open-source solution to combat visual misinformation. This model achieves lightweight and highly accurate detection through fine-tuning a pre-trained model.

Computer VisionSafetensors

xLSTM-7b-Instruct is an experimental fine-tuned version based on NX-AI/xLSTM-7b, specifically optimized for instruction-following tasks. This model adds support for chat templates and uses TRL for supervised fine-tuning training, aiming to provide a better conversational interaction experience.

Natural Language ProcessingTransformers

WEBGEN DEVSTRAL IMAGES is an AI model focused on web page generation. It can generate single-page web pages using HTML, CSS, JS, and Tailwind technologies. This project is trained based on custom templates and uses the supervised fine-tuning method, training with a dataset generated by GPT-OSS-120B.

Natural Language ProcessingTransformersEnglish

This model is based on GPT-OSS-20B and fine-tuned using the Unsloth reinforcement learning framework. The aim is to optimize inference efficiency and reduce vulnerabilities that occur during reinforcement learning from human feedback (RLHF) training. The fine-tuning process focuses on the robustness and efficiency of alignment, ensuring that the model maintains inference depth without incurring excessive computational overhead.

Natural Language ProcessingTransformersEnglish

This is an image-to-video LoRA model trained based on the Qwen/Qwen-Image base model. It uses the LoRA (Low-Rank Adaptation) technology to achieve efficient fine-tuning and can be used for related tasks such as AI image generation.

MultimodalDiffusers

DINOv3 is a series of general visual foundation models developed by Meta AI. Without fine-tuning, it can outperform specialized state-of-the-art models in a wide range of visual tasks. This model uses self-supervised learning to generate high-quality dense features and performs excellently in various tasks such as image classification, segmentation, and depth estimation.

Computer VisionTransformersEnglish

DINOv3 is a versatile visual foundation model developed by Meta AI. It can outperform specialized models in a wide range of visual tasks without fine-tuning. This model can generate high-quality dense features and performs excellently in various visual tasks, significantly surpassing previous self-supervised and weakly supervised foundation models.

Computer VisionTransformersEnglish

DINOv3 is a series of general visual foundation models developed by Meta AI. It can outperform specialized advanced models in various visual tasks without fine-tuning. The model adopts the Vision Transformer architecture and is pre-trained on 1.689 billion web images. It can generate high-quality dense features and performs excellently in tasks such as image classification, segmentation, and retrieval.

Computer VisionTransformersEnglish

TARS-SFT-7B is a security reasoning model based on supervised fine-tuning. It serves as the basic model for reinforcement learning training and is specifically designed to enhance the security of AI systems. This model starts training from Qwen2.5-7B-Instruct and uses the reasoning process as an adaptive defense mechanism to improve the security performance of the model.

Natural Language ProcessingTransformersEnglish

OLMo 2 1B is a post-training variant of the allenai/OLMo-2-0425-1B-RLVR1 model, undergoing supervised fine-tuning, DPO training, and RLVR training, aiming to achieve state-of-the-art performance across multiple tasks.

Natural Language ProcessingTransformersEnglish

A medical diagnosis AI model optimized through LoRA fine-tuning and 4-bit quantization technology based on the Mistral-7B language model, focusing on symptom analysis and disease diagnosis assistance.

Natural Language ProcessingTransformersEnglish

Fin-LLaMA 3.1 8B is a large language model fine-tuned specifically for financial news data based on the LLaMA 3.1 architecture. This model uses the Unsloth library for efficient fine-tuning, adopts LoRA adapter technology, and provides multiple quantized GGUF formats, aiming to generate coherent and relevant financial, economic, and business text responses.

Natural Language ProcessingTransformers

Cymist2-v0.1 is an advanced language model developed by Cypien AI team, specifically optimized for Turkish and English text generation tasks, supporting Retrieval-Augmented Generation (RAG) and Supervised Fine-Tuning (SFT).

Natural Language ProcessingTransformersMultiple Languages

The gpt2-chatbot is a dialogue model obtained through supervised fine-tuning (SFT) on the Deita dataset based on the GPT2-XL architecture, aiming to change a certain decision tendency. This model supports multi-turn dialogue and performs well in text generation tasks, but has limitations in mathematical reasoning.

Natural Language ProcessingTransformers