Use try-except for flash_attn import

This PR is to avoid transformers hard check failure on import dependencies.
If user doesn't install flash_attn, they will not pass the import check for flash_attn. Also same for non-cuda users.

To solve this, we can see that try-except content will be filtered out: https://github.com/huggingface/transformers/blob/main/src/transformers/dynamic_module_utils.py#L155.

modeling_deepseek.py

@@ -48,7 +48,6 @@ from transformers.pytorch_utils import (
 from transformers.utils import (
  add_start_docstrings,
  add_start_docstrings_to_model_forward,
- is_flash_attn_2_available,
  is_flash_attn_greater_or_equal_2_10,
  logging,
  replace_return_docstrings,
@@ -58,10 +57,11 @@ from .configuration_deepseek import DeepseekV2Config
 import torch.distributed as dist
 import numpy as np
 
-if is_flash_attn_2_available():
+try:
  from flash_attn import flash_attn_func, flash_attn_varlen_func
  from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input # noqa
-
+except ImportError:
+ pass
 
 # This makes `_prepare_4d_causal_attention_mask` a leaf function in the FX graph.
 # It means that the function will not be traced through and simply appear as a node in the graph.
@@ -338,7 +338,6 @@ def rotate_half(x):
 # Copied from transformers.models.llama.modeling_llama.apply_rotary_pos_emb
 def apply_rotary_pos_emb(q, k, cos, sin, position_ids, unsqueeze_dim=1):
  """Applies Rotary Position Embedding to the query and key tensors.
-
  Args:
  q (`torch.Tensor`): The query tensor.
  k (`torch.Tensor`): The key tensor.
@@ -1076,7 +1075,6 @@ class DeepseekV2FlashAttention2(DeepseekV2Attention):
  """
  Calls the forward method of Flash Attention - if the input hidden states contain at least one padding token
  first unpad the input, then computes the attention scores and pad the final attention scores.
-
  Args:
  query_states (`torch.Tensor`):
  Input query states to be passed to Flash Attention API
@@ -1287,11 +1285,9 @@ DeepseekV2_START_DOCSTRING = r"""
  This model inherits from [`PreTrainedModel`]. Check the superclass documentation for the generic methods the
  library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads
  etc.)
-
  This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass.
  Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage
  and behavior.
-
  Parameters:
  config ([`DeepseekV2Config`]):
  Model configuration class with all the parameters of the model. Initializing with a config file does not
@@ -1330,50 +1326,38 @@ DeepseekV2_INPUTS_DOCSTRING = r"""
  input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`):
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide
  it.
-
  Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
  [`PreTrainedTokenizer.__call__`] for details.
-
  [What are input IDs?](../glossary#input-ids)
  attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
-
  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.
-
  [What are attention masks?](../glossary#attention-mask)
-
  Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
  [`PreTrainedTokenizer.__call__`] for details.
-
  If `past_key_values` is used, optionally only the last `input_ids` have to be input (see
  `past_key_values`).
-
  If you want to change padding behavior, you should read [`modeling_opt._prepare_decoder_attention_mask`]
  and modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more
  information on the default strategy.
-
  - 1 indicates the head is **not masked**,
  - 0 indicates the head is **masked**.
  position_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
  Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0,
  config.n_positions - 1]`.
-
  [What are position IDs?](../glossary#position-ids)
  past_key_values (`Cache` or `tuple(tuple(torch.FloatTensor))`, *optional*):
  Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
  blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values`
  returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`.
-
  Two formats are allowed:
  - a [`~cache_utils.Cache`] instance;
  - Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of
  shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`). This is also known as the legacy
  cache format.
-
  The model will output the same cache format that is fed as input. If no `past_key_values` are passed, the
  legacy cache format will be returned.
-
  If `past_key_values` are used, the user can optionally input only the last `input_ids` (those that don't
  have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `input_ids`
  of shape `(batch_size, sequence_length)`.
@@ -1402,7 +1386,6 @@ DeepseekV2_INPUTS_DOCSTRING = r"""
 class DeepseekV2Model(DeepseekV2PreTrainedModel):
  """
  Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`DeepseekV2DecoderLayer`]
-
  Args:
  config: DeepseekV2Config
  """
@@ -1638,20 +1621,14 @@ class DeepseekV2ForCausalLM(DeepseekV2PreTrainedModel):
  Labels for computing the masked language modeling loss. Indices should either be in `[0, transformers.,
  config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
  (masked), the loss is only computed for the tokens with labels in `[0, transformers., config.vocab_size]`.
-
  Returns:
-
  Example:
-
  ```python
  >>> from transformers import AutoTokenizer, DeepseekV2ForCausalLM
-
  >>> model = DeepseekV2ForCausalLM.from_pretrained(PATH_TO_CONVERTED_WEIGHTS)
  >>> tokenizer = AutoTokenizer.from_pretrained(PATH_TO_CONVERTED_TOKENIZER)
-
  >>> prompt = "Hey, are you conscious? Can you talk to me?"
  >>> inputs = tokenizer(prompt, return_tensors="pt")
-
  >>> # Generate
  >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
  >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
@@ -1793,10 +1770,8 @@ class DeepseekV2ForCausalLM(DeepseekV2PreTrainedModel):
 @add_start_docstrings(
  """
  The DeepseekV2 Model transformer with a sequence classification head on top (linear layer).
-
  [`DeepseekV2ForSequenceClassification`] uses the last token in order to do the classification, as other causal models
  (e.g. GPT-2) do.
-
  Since it does classification on the last token, it requires to know the position of the last token. If a
  `pad_token_id` is defined in the configuration, it finds the last token that is not a padding token in each row. If
  no `pad_token_id` is defined, it simply takes the last value in each row of the batch. Since it cannot guess the