ue-expert-v2
Fine-tuned Unreal Engine 5 expert model, specialized in C++ and Blueprint development. — Base model: Qwen2.5-Coder-14B-Instruct — Fine-tuning:...
Fine-tuned Unreal Engine 5 expert model, specialized in C++ and Blueprint development. — Base model: Qwen2.5-Coder-14B-Instruct — Fine-tuning:...
A fine-tuned version of Qwen2.5-3B-Instruct specifically designed for advanced cybersecurity analysis. This model is built to bridge the...
Qwen2.5-Coder-3B, точно настроенный на данные смарт-контракта Cardano / Aiken, преобразованный в 4-разрядный формат Apple MLX для быстрого вывода...
> Results obtained via local evaluation. Given the model size (0.2B parameters), low benchmark scores are expected. —...
SAM-1-Base (Shopping Agent Model) is a 7.6B parameter language model fine-tuned for commerce reasoning tasks, developed by SnapCart...
SEAD (Self-Evolving Agent for Service Dialogue) — это коэволюционная структура обучения с подкреплением, предназначенная для обучения агентов диалога,...
Fine-tuned LoRA on DeepSeek-R1-Distill-Qwen-1.5B for Dyck language completion with step-by-step reasoning. The model completes balanced bracket sequences (Dyck...
A 1.5B parameter model for next-edit autocomplete, quantized to 8bit MLX format. Sweep Next-Edit predicts your next code...
LumiChats is revolutionizing AI access for students, developers, and creators worldwide. Founded by Aditya Kumar Jha, we’re on...
We present SciRM and SciRM-Ref, cost-efficient open-source reward models tailored for scientific writing evaluation. Our models are trained...