Update bloom attention forward reshape follwing the transformer change

[yeonsily]

What does this PR do?

https://github.com/huggingface/transformers/blob/main/src/transformers/models/bloom/modeling_bloom.py#L262 _reshape() function covers OH transpose change. No need to transpose in OH.

The current code is failed at text-getneration CI.

CI run command: python3 /root/optimum-habana/examples/text-generation/run_generation.py --model_name_or_path bigscience/bloomz-7b1 --batch_size 1 --use_kv_cache --max_new_tokens 100 --use_hpu_graphs --bf16

Error message:
File "/usr/local/lib/python3.10/dist-packages/optimum/habana/transformers/models/bloom/modeling_bloom.py", line 142, in gaudi_bloom_attention_forward
query_layer = query_layer.transpose(1, 2).reshape(batch_size * self.num_heads, q_length, self.head_dim)
RuntimeError: shape '[32, 32, 128]' is invalid for input of size 438272

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?