This is a video action recognition model fine-tuned on the WLASL dataset based on the VideoMAE-Base architecture. After 200 epochs of training, it achieved a top-1 accuracy of 52.96% and a top-5 accuracy of 79.88% on the evaluation set, specifically designed for sign language action recognition tasks.

Computer VisionTransformers

This model is a professional code generation model fine-tuned on the swe_only_sweagent dataset based on Qwen2.5-Coder-32B-Instruct. It achieved a loss value of 0.1210 on the evaluation set and is specifically optimized for software engineering-related tasks.

Natural Language ProcessingTransformers

This is a classifier model fine-tuned based on the jhu-clsp/mmBERT-small model, achieving an accuracy of 91.07% on the evaluation set. It is mainly used for text classification tasks.

Natural Language ProcessingPeft

G²RPO is a novel reinforcement learning framework specifically designed for preference alignment in flow models, significantly improving the generation quality through a granular reward evaluation mechanism.

MultimodalDiffusers

This is a text classification model fine-tuned based on the mmBERT-small architecture, specifically designed for the message type classification task. It achieved an accuracy of 93.94% on the evaluation set and has efficient text classification capabilities.

Natural Language ProcessingPeft

Sunflower-14B is a multilingual large language model developed by Sunbird AI, specifically designed for Ugandan languages. This model is built on the Qwen 3-14B architecture and supports translation and text generation tasks for 31 Ugandan languages and English, performing excellently in multiple evaluations.

Natural Language ProcessingTransformersMultiple Languages

This model is a video understanding model based on the VideoMAE-Large architecture, pre-trained on the Kinetics dataset and then fine-tuned on an unknown dataset. It achieved an accuracy of 85.86% and a loss value of 0.7987 on the evaluation set, demonstrating excellent video classification ability.

Computer VisionTransformers

This is a license plate detection model fine - tuned based on the DETR architecture and the DINOv3 visual backbone network. It achieved a loss value of 2.7008 on the evaluation set and is specifically designed for license plate recognition tasks.

Computer VisionTransformers

Qwen3-4B-I-1509 is a dedicated model fine-tuned based on the Qwen3-4B-Instruct-2507 base model, focusing on tool usage and function call generation tasks. This model is trained using a reinforcement learning method with multi-signal rewards and demonstrates good performance in multiple evaluation benchmarks.

Natural Language ProcessingTransformersEnglish

This model is a large language model fine-tuned on a specific dataset based on Qwen/Qwen3-8B. It achieved a loss value of 0.2248 on the evaluation set and has improved natural language processing capabilities.

Natural Language ProcessingTransformers

This is a large language model fine-tuned based on Qwen2.5-7B-Instruct. It was trained on the C2_re_100k_tag5_cleaned_hermes_toolv6_dethink_replacedv1 dataset and achieved a loss value of 0.2549 on the evaluation set. It has optimized dialogue and tool usage capabilities.

Natural Language ProcessingTransformers

This model is a large language model fine-tuned on the 2and3_apps_30k_v6 dataset based on Qwen/Qwen2.5-7B-Instruct. It achieved a loss value of 0.1593 on the evaluation set, showing good performance.

Natural Language ProcessingTransformers

ScamGuard is a fraud information detection model fine-tuned based on bert-base-cased. The accuracy on the evaluation set reaches 98.13%. It can effectively identify fraud information and improve the accuracy and efficiency of detection.

Natural Language ProcessingTransformers

DeepSeek-GRM-16B is a generative reward model based on Self-Principled Critique Tuning (SPCT), which can generate a transparent 'Principle → Critique → Score' evaluation process for query-responses and can be used in tasks such as reinforcement learning, evaluation, and data collection of large language models.

Natural Language ProcessingTransformersMultiple Languages

This is an experimental quantized formula model that converts the original GLM-4.5-Air model to the MLX format, using a mixed precision quantization strategy (4 - 8 bits), optimized specifically for text generation tasks, and is currently still in the evaluation stage.

Natural Language ProcessingMlxMultiple Languages

This is a vulnerability classification model fine-tuned based on RoBERTa-base, specifically designed for the CWE (Common Weakness Enumeration) parent vulnerability classification task. It achieved an accuracy of 87.5% and an F1 macro value of 0.6248 on the evaluation set, providing effective support for software security vulnerability analysis.

Natural Language ProcessingTransformers

GLM-4.5 is a foundation model designed for intelligent agents, integrating inference, coding, and intelligent agent capabilities. It has a total of 355 billion parameters and ranks 3rd in 12 industry-standard benchmark evaluations, scoring 63.2. It uses the MIT open-source license and can be used for commercial purposes and secondary development.

Natural Language ProcessingTransformersMultiple Languages

Seed-X-RM-7B is a reward model in the Seed-X series, specifically designed to evaluate translation quality. Based on the 7-billion-parameter Mistral architecture, this model can assign reward scores to multilingual translations and supports the evaluation of translation quality among 25 languages.

Natural Language ProcessingSafetensors

This is a quantized version of the judgment model with 32B parameters, suitable for tasks such as model evaluation, reward modeling, and text sorting.

Natural Language ProcessingTransformersEnglish

The static quantization version of CompassJudger-2-32B-Instruct, suitable for tasks such as model judgment, evaluation, reward modeling, and text sorting.

Natural Language ProcessingTransformersEnglish