> This repository contains an FP8 quantized version of the Kwaipilot/KAT-Dev model. 🔥 We’re thrilled to announce the release of KAT-Dev-72B-Exp, our latest and most powerful model yet! 🔥 You can now try our strongest proprietary coder model KAT-Coder directly on the StreamLake platform for free. KAT-Dev-32B is an open-source 32B-parameter model for software engineering tasks. On SWE-Bench Verified, KAT-Dev-32B achieves comparable performance with 62.4% resolved and ranks 5th among all open-source models with different scales. KAT-Dev-32B is optimized via several stages of training, including a mid-training stage, supervised fine-tuning (SFT) & reinforcement fine-tuning (RFT) stage and an large-scale agentic reinforcement learning (RL) stage. In summary, our contributions include: Stage Key Techniques 1. Mid-Training We observe that adding extensive training for tool-use capability, multi-turn interaction, and instruction-following at this stage may not yield large performance gains in the current results (e.g., on leaderboards like SWE-bench). However, since our experiments are based on the Qwen3-32B model, we find that enhancing these foundational capabilities will have a…
Модальности:
Генерация текста
Области применения:
Диалог / чат Мультиязычность
Задача: Генерация текста
Автор: Kwaipilot
Теги: qwen3, conversational, multilingual, text-generation-inference, endpoints_compatible, compressed-tensors
Лайков: 4 | Загрузок: 23
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
