初始化项目，由ModelHub XC社区提供模型

Model: xformAI/facebook-opt-125m-qcqa-ub-6-best-for-KV-cache
Source: Original Platform

README.md

@@ -0,0 +1,9 @@
+---
+license: mit
+language:
+- en
+library_name: transformers
+---
+
+
+This is a QCQA version of the original model facebook/opt-125m. In this version, the original MHA architecture is preserved but instead of having a single K/V head, different K/V heads corresponding to the same group have the same mean-pooled K or V values. It has upto 6 groups of KV heads per layer instead of original 12 KV heads in the MHA implementation. This implementation is supposed to more efficient than corresponding GQA one.