yejingfu's picture
Add ReadMe note
0b5bf00
|
raw
history blame
350 Bytes
metadata
license: mit

=== About This model is a research project by Novita AI, focusing on optimizing large language model inference efficiency while maintaining high performance. The DeepSeek-R1-Distill-Llama-70B model implements innovative quantization techniques to achieve significant throughput improvements without compromising accuracy.