fix falcon-40b accuracy issue

[Yejing-Lai]

"FalconDecoderLayer" module will choose the "glmtype" fused_qkv_type. But the Falcon model should use the "bloomtype".

[delock]

@Yejing-Lai can you add text output before/after your fix for documentation purpose? Thanks!

[Yejing-Lai]

before fix output: ('DeepSpeed is a machine learning framework for deep neural networks (DNNs) and deep reinforcement learning (DRL). It is written in C++ and is e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e', 32)

after fix output:('DeepSpeed is a machine learning framework for deep neural networks (DNNs) and deep reinforcement learning (DRL). It is written in C++ and is based on PyTorch.\nDeepSpeed is designed to scale DNNs and DRL to large numbers of GPUs and TPUs.\nDeepSpeed is', 32)

[delock]

before fix output: ('DeepSpeed is a machine learning framework for deep neural networks (DNNs) and deep reinforcement learning (DRL). It is written in C++ and is e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e', 32)

after fix output:('DeepSpeed is a machine learning framework for deep neural networks (DNNs) and deep reinforcement learning (DRL). It is written in C++ and is based on PyTorch.\nDeepSpeed is designed to scale DNNs and DRL to large numbers of GPUs and TPUs.\nDeepSpeed is', 32)

Thanks!

[delock]

@Yejing-Lai is this PR already submitted to upstream?