This model is a text generation model fine-tuned based on Meta's Llama-3.1 architecture. It is trained using reinforcement learning with the TRL library and the GRPO (Group Relative Policy Optimization) method, and is specifically optimized for argument generation tasks.

Natural Language ProcessingTransformers

Qwen-1.5B_THIP is a mathematical reasoning model fine-tuned using the GRPO method on the DeepMath-103k mathematical dataset based on DeepSeek-R1-Distill-Qwen-1.5B with the TRL framework. This model is specifically optimized for solving mathematical problems and has strong mathematical reasoning abilities.

Natural Language ProcessingTransformers

GTA1 is a GUI grounding model trained based on GRPO reinforcement learning, specifically designed for graphical user interface automation operations. Compared with methods that rely on long chains of thought reasoning, GRPO directly incentivizes actionable and well-founded responses, demonstrating excellent grounding performance in multiple benchmark tests.

MultimodalTransformersEnglish

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

GTA1 is a state-of-the-art GUI grounding model trained based on reinforcement learning (GRPO), specifically designed for graphical user interface automation tasks. Different from methods that rely on long thought-chain reasoning, GRPO directly incentivizes actionable and well-founded responses, demonstrating excellent grounding performance and agent performance on multiple challenging datasets.

MultimodalTransformersEnglish

A three-stage training GRPO inference test model based on the microsoft/phi-4 (14B) base model, fine-tuned through the SFT→RLHF→SFT process, with excellent multi-step reasoning ability

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

This is a language model specifically optimized for the Indonesian legal field. It is fine-tuned on the Indonesian legal Q&A dataset using the GRPO method based on DeepSeek-R1-0528-Qwen3-8B, focusing on improving legal reasoning and structured thinking abilities.

Natural Language ProcessingTransformers

This model is a fine-tuned version based on DeepSeek-R1-0528-Qwen3-8B, trained using TRL and GRPO methods, focusing on improving mathematical reasoning ability.

Natural Language ProcessingTransformersMultiple Languages

Magistral-Small-2506-Vision is an inference fine-tuned version based on Mistral Small 3.1 with GRPO training, an experimental checkpoint with visual capabilities.

MultimodalSafetensorsMultiple Languages

GTA1 is a state-of-the-art GUI positioning model trained based on Reinforcement Learning (GRPO). It achieves precise interface element positioning by directly motivating actionable responses rather than lengthy inferences.

MultimodalTransformers

This is a fine-tuned version based on the Qwen-14B model, trained using the GRPO method, suitable for text generation tasks.

Natural Language ProcessingTransformers

GTA1 is a GUI positioning model based on Reinforcement Learning (GRPO). It achieves precise positioning by directly rewarding successful clicks, avoiding lengthy thought-chain reasoning.

MultimodalTransformers

J-1 is a reasoning model based on the Gemma 3 4-B model, trained on Italian mathematical and reasoning problems using the GRPO method. On the Invalsi ITA test dataset, the performance has been improved from 57% of the base model to 79%, significantly enhancing the Italian reasoning ability.

Natural Language ProcessingTransformersOther

INTELLECT 2 is a large language model launched by PrimeIntellect, supporting a context length of 40960 tokens, trained using the QwQ architecture and GRPO reinforcement learning framework.

Natural Language ProcessingGguf

E1-Math-1.5B is a language model fine-tuned based on DeepSeek-R1-Distilled-Qwen-1.5B, supporting elastic reasoning and the GRPO method, suitable for budget-constrained deduction scenarios.

Natural Language ProcessingTransformers

This model is a large language model for medical Q&A fine-tuned using the GRPO method on the medmcqa-grpo dataset based on Qwen/Qwen3-4B. It is specifically optimized for the scenario of medical multiple-choice questions and has strong medical reasoning ability.

Natural Language ProcessingTransformers

Vietnamese Retrieval-Augmented Generation (RAG) specialized large model fine-tuned based on Qwen2.5-7B-Instruct, trained using GRPO optimization method

Natural Language ProcessingTransformersOther

XiYanSQL-QwenCoder-3B-2504 is the latest SQL generation model released by XGenerationLab. Optimized through fine-tuning and GRPO training, it supports multiple dialects and delivers efficient and accurate SQL generation capabilities.

Natural Language ProcessingSafetensorsMultiple Languages

XiYanSQL-QwenCoder-2504 is the latest SQL generation model that combines fine-tuning and GRPO training. It combines efficiency and accuracy in SQL generation, supports multiple dialects, and is ready to use out of the box. It performs excellently on different dialects and out-of-domain datasets.

Natural Language ProcessingSafetensorsMultiple Languages