Microsoft's Deberta Xlarge Mnli is a chat model fine-tuned for natural language understanding tasks, particularly exceling at text generation. Its disentangled attention mechanism and enhanced mask decoder enable strong performance on tasks like MNLI, with an accuracy of 91.5/91.2. Notably, this model has a context window of 512 tokens, allowing it to process relatively long input sequences.
Input
Output
Context
1K
Max Output
1K
Parameters
1.5B
Input Modalities
Output Modalities
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Automatically route workloads to the right model for every task, every time.