jSUtSrSSKrSSKJr SSKJr SSKrSSKJrJ r Sr \"SS 55r SS \RS-S \R\-\-S \RS \S\S-4 SjjrSS \RS-S \R\-\-S \RS \S\S-4 SjjrSS\RS\R&S\S-4SjjrSS\RS\R&S\S-4SjjrSS \R\-\-S\R&S\R,S \S\S-S\RS-4 Sjjrg)a IMPORTANT NOTICE: Every class and function in this file is deprecated in favor of using the much more general `masking_utils.py` primitives. New code should not rely on it, it is only kept for backward compatibility for now, and will be removed in the future. N) dataclass)Union)is_torchdynamo_compiling is_tracingzThe attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.c\rSrSr%Sr\\S'\\S'SS\S\S-4SjjrS S\S\S \S \ RS \ \ RS 4S \ RS-4 SjjrSS\ RS\S \ RS \S-S \ R4 Sjjr\S!S\ R"S \ RS \ RS\S\S-4 Sjj5r\SS\ RS \ RS\S-4Sjj5r\S\ R(S\4Sj5r\S"S\ RS-S\ RS\S\S-S\S \4 Sjj5rSrg)#AttentionMaskConverter#a A utility attention mask class that allows one to: - Create a causal 4d mask - Create a causal 4d mask with slided window - Convert a 2d attention mask (batch_size, query_length) to a 4d attention mask (batch_size, 1, query_length, key_value_length) that can be multiplied with attention scores Examples: ```python >>> import torch >>> from transformers.modeling_attn_mask_utils import AttentionMaskConverter >>> converter = AttentionMaskConverter(True) >>> converter.to_4d(torch.tensor([[0, 0, 0, 1, 1]]), 5, key_value_length=5, dtype=torch.float32) tensor([[[[-3.4028e+38, -3.4028e+38, -3.4028e+38, -3.4028e+38, -3.4028e+38], [-3.4028e+38, -3.4028e+38, -3.4028e+38, -3.4028e+38, -3.4028e+38], [-3.4028e+38, -3.4028e+38, -3.4028e+38, -3.4028e+38, -3.4028e+38], [-3.4028e+38, -3.4028e+38, -3.4028e+38, 0.0000e+00, -3.4028e+38], [-3.4028e+38, -3.4028e+38, -3.4028e+38, 0.0000e+00, 0.0000e+00]]]]) ``` Parameters: is_causal (`bool`): Whether the attention mask should be a uni-directional (causal) or bi-directional mask. sliding_window (`int`, *optional*): Optionally, the sliding window masks can be created if `sliding_window` is defined to a positive integer. is_causalsliding_windowNc[R"[[5 XlX lUR b*UR S::a[ SUR S35egg)NrzaMake sure that when passing `sliding_window` that its value is a strictly positive integer, not ``)warningswarnDEPRECATION_MESSAGE FutureWarningr r ValueError)selfr r s ڳC:\Users\johnn\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\LocalCache\local-packages\Python313\site-packages\transformers/modeling_attn_mask_utils.py__init__AttentionMaskConverter.__init__Fss )=9",    *t/B/Ba/GstxuHuHtIIJK 0H * batch_size query_lengthkey_value_lengthdtypedevicestrreturncUR(d[SURS35eX4nX2- nSnUSS:d URbUR UUUUURS9nU$)z Creates a causal 4D mask of (bsz, head_dim=1, query_length, key_value_length) shape and adds large negative bias to upper right hand triangular matrix (causal mask). z"Please use `to_causal_4d` only if z has `is_causal` set to True.Nrrpast_key_values_lengthr )r r __class__r _make_causal_mask) rrrrrr input_shaper#causal_4d_masks r to_causal_4d#AttentionMaskConverter.to_causal_4dQs~~A$..AQQnop p"0 !1!@ r?Q $"5"5"A!33'=#22 4Nrattention_mask_2dcURSU4nSnUSS:d URbKUR(a:Uc [S5eXB- nUR UUUR UURS9nOURb [ S5eURXUSS9RUR 5nUb>URUR5[R"U5R5nUn U $) z Converts 2D attention mask to 4D attention mask by expanding mask to (bsz, head_dim=1, query_length, key_value_length) shape and by adding a large negative bias to not-attended positions. If attention_mask is causal, a causal mask will be added. rNr!rzpThis attention mask converter is causal. Make sure to pass `key_value_length` to correctly create a causal mask.r"z?Sliding window is currently only implemented for causal masking)tgt_len)shaper r rr%rNotImplementedError _expand_maskto masked_fillbooltorchfinfomin) rr*rrrr&r'r#expanded_attn_maskexpanded_4d_masks rto_4dAttentionMaskConverter.to_4drs%)..q1<@  Oa 4#6#6#B' G&6%D "!33(//'=#22 4N ,%&gh h"../@Q\]_Q`.add  $ $   %!/!;!;  )1}&:&:499R=!&LLaPwwu~ !A %99ekk'QVfhlmsuvD  %->BH ::eood%**&MX`aL())zz|   lEKK,>,B,B CD$1$%,,S!WH^>^__rrLr,c[R"[[5 UR 5up4UbUOUnUSS2SSSS24R USX$5R U5n[R"SUS9U- nURUR [R5[R"U5R5$)zW Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`. Nr?r>) rrrrrBrJr0r3tensorr1r2r4r5)rLrr,rKsrc_len expanded_mask inverted_masks rr/#AttentionMaskConverter._expand_masks  )=9yy{ $0'gQdA-.55c1gORRSXY  S6F (()9)9%**)Eu{{SXGYG]G]^^rrT min_dtypec[R"[[5 UR[ R :Xa [S5eUR[ R"X:HSSS9)5$)a Attend to all tokens in masked rows from the expanded attention mask, for example the relevant first rows when using left padding. This is required by F.scaled_dot_product_attention memory-efficient attention path. Details: https://github.com/pytorch/pytorch/issues/110213 `expanded_mask` is [bsz, num_masks, tgt_seq_len, src_seq_len] or [bsz, tgt_seq_len, src_seq_len]. `attention_mask` is [bsz, src_seq_len]. The dimension num_masks of `expanded_mask` is most often 1, but it can also be the number of heads in the case of alibi attention bias. For example, if `expanded_mask` is (e.g. here left-padding case) ``` [[[[0, 0, 0], [0, 0, 0], [0, 0, 1]]], [[[1, 0, 0], [1, 1, 0], [1, 1, 1]]], [[[0, 0, 0], [0, 1, 0], [0, 1, 1]]]] ``` then the modified `expanded_mask` will be ``` [[[[1, 1, 1], <-- modified [1, 1, 1], <-- modified [0, 0, 1]]], [[[1, 0, 0], [1, 1, 0], [1, 1, 1]]], [[[1, 1, 1], <-- modified [0, 1, 0], [0, 1, 1]]]] ``` z\AttentionMaskConverter._unmask_unattended expects a float `expanded_mask`, got a BoolTensor.r!T)r=keepdim) rrrrrr3r2rmulall)rTrWs r_unmask_unattended)AttentionMaskConverter._unmask_unattendeds_R  )=9   %** ,n   %))M,FBX\"]!]^^rattention_mask inputs_embeds is_trainingc[R"[[5 URSURSpeXb-n[ U5nSn Uc%U(dU(dUS:XdXv:Xa UbXs:aSn U $UbXs:aL[ UR5S:XagU(d+[R"US:H5(a US:XdXv:XaSn U $)a Detects whether the optional user-specified attention_mask & the automatically created causal mask can be ignored in case PyTorch's SDPA is used, rather relying on SDPA's `is_causal` argument. In case no token is masked in the `attention_mask` argument, if `query_length == 1` or `key_value_length == query_length`, we rather rely on SDPA `is_causal` argument to use causal/non-causal masks, allowing to dispatch to the flash attention kernel (that can otherwise not be used if a custom `attn_mask` is passed). rrFT) rrrrr-rlenr3r[) r^r_r#r r`_rr is_tracing_ignore_causal_masks r_ignore_causal_mask_sdpa/AttentionMaskConverter._ignore_causal_mask_sdpas"  )=9'--a0-2E2Ea2H<'@ / "  !K!Q&*:*J#+/?/P%)""! #'7'H>''(A- UYY~/B%C%C1$(8(H)-&"!rr r N)cpurN)NF)__name__ __module__ __qualname____firstlineno____doc__r2__annotations__intrr3rrrTensorr(r8 staticmethodSizer%r/ FloatTensorfloatr\rg__static_attributes__rrr r #s<O $ d ".3   {{  ellE)*   L(, -  <<- - {{ - * -  - ^ '(%) !`!`{{!` !`!$ !` d !`!`F _5<< _ _cDj _ _0_((0_0_0_d &*! 8" t+8"||8"!$8"d 8"  8"  8"8"rr r^r&r_r#r c[SUS9nUSU-nUb8[UR5S:XaURXSXbRS9nU$Ub[UR5S:XaUSSUSU4n[ UR5U:wa%[ S [ UR5S US 35eS U- nURUR[R5[R"UR5R5nU$URUSUSXbRURS 9nU$)a Creates a causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape `(batch_size, key_value_length)` Args: attention_mask (`torch.Tensor` or `None`): A 2D attention mask of shape `(batch_size, key_value_length)` input_shape (`tuple(int)` or `list(int)` or `torch.Size`): The input shape should be a tuple that defines `(batch_size, query_length)`. inputs_embeds (`torch.Tensor`): The embedded inputs as a torch Tensor. past_key_values_length (`int`): The length of the key value cache. sliding_window (`int`, *optional*): If the model uses windowed attention, a sliding window should be passed. Trir!)rrrbrrz#Incorrect 4D attention_mask shape: z ; expected: .rQr<)r rcr-r8rtuplerr1r0r3r2r4r5r(r) r^r&r_r#r attn_mask_converterrexpected_shaperUs r!_prepare_4d_causal_attention_maskrDsg.14P^_"2)??!c.*>*>&?1&D,22 O>NViVi3 ( #  #N,@,@(AQ(F%a.![^=MN %% &. 85eNrs ! Dw  ]"]" ]"J "& 1LL4'1e#d*1<<1 1 $J 1t"& 7LL4'7e#d*7<<7 7 $J 7t XU\\ X%++ XPSVZPZ X \ell\5;;\Y\_cYc\:#$!% e#d* ;; LL  $J   \\D r