L i d dl mZmZ d dlmZ d dlmZmZ d dlZ d dl
Z
ddl m Z m
Z
ddlmZmZ e
j" e Zd Zd
Z G d d e Z G d
de Z G d de Z G d d Zy) )ABCabstractmethod)UserDict)OptionalUnionN )add_start_docstringslogging )
ConstraintConstraintListStatea
Args:
input_ids (`torch.LongTensor` of shape `(batch_size * num_beams, sequence_length)`):
Indices of input sequence tokens in the vocabulary.
Indices can be obtained using any class inheriting from [`PreTrainedTokenizer`]. See
[`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details.
[What are input IDs?](../glossary#input-ids)
next_scores (`torch.FloatTensor` of shape `(batch_size, 2 * num_beams)`):
Current scores of the top `2 * num_beams` non-finished beam hypotheses.
next_tokens (`torch.LongTensor` of shape `(batch_size, 2 * num_beams)`):
`input_ids` of the tokens corresponding to the top `2 * num_beams` non-finished beam hypotheses.
next_indices (`torch.LongTensor` of shape `(batch_size, 2 * num_beams)`):
Beam indices indicating to which beam hypothesis the `next_tokens` correspond.
pad_token_id (`int`, *optional*):
The id of the *padding* token.
eos_token_id (`Union[int, list[int]]`, *optional*):
The id of the *end-of-sequence* token. Optionally, use a list to set multiple *end-of-sequence* tokens.
beam_indices (`torch.LongTensor`, *optional*):
Beam indices indicating to which beam hypothesis each token correspond.
Return:
`UserDict`: A dictionary composed of the fields as defined above:
- **next_beam_scores** (`torch.FloatTensor` of shape `(batch_size * num_beams)`) -- Updated scores of all
non-finished beams.
- **next_beam_tokens** (`torch.FloatTensor` of shape `(batch_size * num_beams)`) -- Next tokens to be added
to the non-finished beam_hypotheses.
- **next_beam_indices** (`torch.FloatTensor` of shape `(batch_size * num_beams)`) -- Beam indices
indicating to which beam the next tokens shall be added.
a
Args:
input_ids (`torch.LongTensor` of shape `(batch_size * num_beams, sequence_length)`):
Indices of input sequence tokens in the vocabulary.
Indices can be obtained using any class inheriting from [`PreTrainedTokenizer`]. See
[`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details.
[What are input IDs?](../glossary#input-ids)
final_beam_scores (`torch.FloatTensor` of shape `(batch_size * num_beams)`):
The final scores of all non-finished beams.
final_beam_tokens (`torch.FloatTensor` of shape `(batch_size * num_beams)`):
The last tokens to be added to the non-finished beam_hypotheses.
final_beam_indices (`torch.FloatTensor` of shape `(batch_size * num_beams)`):
The beam indices indicating to which beam the `final_beam_tokens` shall be added.
pad_token_id (`int`, *optional*):
The id of the *padding* token.
eos_token_id (`Union[int, list[int]]`, *optional*):
The id of the *end-of-sequence* token. Optionally, use a list to set multiple *end-of-sequence* tokens.
Return:
`torch.LongTensor` of shape `(batch_size * num_return_sequences, sequence_length)`: The generated sequences.
The second dimension (sequence_length) is either equal to `max_length` or shorter if all batches finished early
due to the `eos_token_id`.
c Z e Zd ZdZe ee dej dej dej dej de
ej f
d Z e ee
dej dej dej dej dedej f d Zy
)
BeamScorerz
Abstract base class for all beam scorers that are used for [`~PreTrainedModel.beam_search`] and
[`~PreTrainedModel.beam_sample`].
input_ids next_scores next_tokens next_indicesreturnc t d NzThis is an abstract method.NotImplementedError)selfr r r r kwargss i/mnt/ssd/data/python-lab/Trading/venv/lib/python3.12/site-packages/transformers/generation/beam_search.pyprocesszBeamScorer.processb s ""?@@
max_lengthc t d r r )r r r r r r r s r finalizezBeamScorer.finalizen s ""?@@r N)__name__
__module__ __qualname____doc__r r PROCESS_INPUTS_DOCSTRINGtorch
LongTensor FloatTensortupleTensorr FINALIZE_INPUTS_DOCSTRINGintr r r r r \ s
23A##A &&A %% A
&& A
u|| A 4 A 34 A## A && A %% A
&& A
A
A 5 Ar r c e Zd ZdZ d dededej dedee e
f ded ed
e e fd Z e
d e fd
Z d dej dej dej dej de eeej" f de eeee ej" f de ej deded ee
ej" f fdZ d dej dej dej dej d
ede eeej" f de eeee ej" f de ej ded eej fdZy) BeamSearchScorera
[`BeamScorer`] implementing standard beam search decoding.
Adapted in part from [Facebook's XLM beam search
code](https://github.com/facebookresearch/XLM/blob/9e6f6814d17be4fe5b15f2e6c43eb2b2d76daeb4/src/model/transformer.py#L529).
Reference for the diverse beam search algorithm and implementation [Ashwin Kalyan's DBS
implementation](https://github.com/ashwinkalyan/dbs/blob/master/dbs/beam_utils.lua)
Args:
batch_size (`int`):
Batch Size of `input_ids` for which standard beam search decoding is run in parallel.
num_beams (`int`):
Number of beams for beam search.
device (`torch.device`):
Defines the device type (*e.g.*, `"cpu"` or `"cuda"`) on which this instance of `BeamSearchScorer` will be
allocated.
length_penalty (`float`, *optional*, defaults to 1.0):
Exponential penalty to the length that is used with beam-based generation. It is applied as an exponent to
the sequence length, which in turn is used to divide the score of the sequence. Since the score is the log
likelihood of the sequence (i.e. negative), `length_penalty` > 0.0 promotes longer sequences, while
`length_penalty` < 0.0 encourages shorter sequences.
do_early_stopping (`bool` or `str`, *optional*, defaults to `False`):
Controls the stopping condition for beam-based methods, like beam-search. It accepts the following values:
`True`, where the generation stops as soon as there are `num_beams` complete candidates; `False`, where an
heuristic is applied and the generation stops when is it very unlikely to find better candidates;
`"never"`, where the beam search procedure only stops when there cannot be better candidates (canonical
beam search algorithm).
num_beam_hyps_to_keep (`int`, *optional*, defaults to 1):
The number of beam hypotheses that shall be returned upon calling
[`~transformers.BeamSearchScorer.finalize`].
num_beam_groups (`int`, *optional*, defaults to 1):
Number of groups to divide `num_beams` into in order to ensure diversity among different groups of beams.
See [this paper](https://huggingface.co/papers/1610.02424) for more details.
max_length (`int`, *optional*):
The maximum length of the sequence to be generated.
N
batch_size num_beamsdevicelength_penaltydo_early_stoppingnum_beam_hyps_to_keepnum_beam_groupsr c t j d || _ || _ || _ || _ || _ || _ | j | j z | _ d| _ t || j z D cg c]/ } t | j | j | j
| 1 c} | _ t j t || j z D cg c] } d c} t j | j | _ t# |t$ r|dk rt' d| d t# |t$ r
||kD s||z dk7 rt' d | d
| d y c c} w c c} w ) Nz`BeamSearchScorer` is deprecated and will be removed in v4.62.0, as constrained beam search has been moved to the Hub: https://hf.co/transformers-community/constrained-beam-search.Fr1 r3 early_stoppingr dtyper2 r A`num_beams` has to be an integer strictly greater than 1, but is G. For `num_beams` == 1, one should make use of `greedy_search` instead.r z`num_beam_groups` has to be an integer smaller or equal than `num_beams` and `num_beams` has to be divisible by `num_beam_groups`, but is z with `num_beams` being .)logger warning_oncer1 r2 r3 r4 r5 r6
group_size_is_initrangeBeamHypotheses
_beam_hypsr& tensorbool_done
isinstancer,
ValueError)
r r0 r1 r2 r3 r4 r5 r6 r _s
r __init__zBeamSearchScorer.__init__ s
C
# ,!2 %:" . ..D,@,@@
:(<(<<=
// # 2 2 # 5 5%
\\ !*t/C/C"C D EqU EUZZ`d`k`k
)S)Y!^ ST]S^ _C C
/3/Oi4OU^apUptuUu ;;J:KKcdmcnnoq
Vv+
Fs ?4E($ E-r c R | j j j S NrH allitemr s r is_donezBeamSearchScorer.is_done zz~~ $$&&r r r r r pad_token_id eos_token_id beam_indices group_indexdecoder_prompt_lenc
|j d dz }
t | j | j z } | |j d | j z k7 ra| j dkD r)t d|j d d| j d t d|j d d| j d |j } t j | | j f|j | }
t j | | j f|j | }t j | | j f|j | }|Bt |t j s(t |t r|g}t j | }t | D ] }|| j z |z }| j | ri| j t | j | k rt d
| j d || t d d|
|d d f< |||d d f< d||d d f< d}t# t% || || || D ] \ }\ }}}|| j z |z }|y|j' |v rg|| j k\ }|rB| || }||fz }nd }| j | j) || j+ |j' ||
| z
n||
||f< ||||f< ||||f< |dz
}|| j k( s n || j k r(t d| j d|| d| d|| d | j | xs? | j | j- || j/ j' |
| | j |< t1 |
j3 d |j3 d |j3 d d S )Nr r zA group beam size of z0 is used as the input, but a group beam size of z is expected by the beam scorer.zA beam size of z* is used as the input, but a beam size of r: #Batch can only be done if at least beams have been generatedMGenerated beams >= num_beams -> eos_token_id and pad_token have to be definedrW
generated_lenAt most tokens in can be equal to `eos_token_id:
`. Make sure are corrected.next_beam_scoresnext_beam_tokensnext_beam_indices)shapelenrE r6 rA rJ r2 r& zerosr; rI r* r, rF rC rH r1 enumerateziprQ addclonerS maxr view)r r r r r rU rV rW rX rY cur_lenr0 r2 rg rh ri batch_idxbatch_group_idxbeam_idxbeam_token_rank
next_token
next_score
next_indexbatch_beam_idx&is_beam_token_worse_than_top_num_beams
beam_indexs r r zBeamSearchScorer.process s= //"%) )T-A-AA
)//!,? @##a' +IOOA,>+? @ # //OQ
!%iooa&8%99c''GI
!! ;;
DOO'DKL]L]flm ;;
DOO'DKL]L]flm !KKT__(E\M_M_hn o #J|U\\,R,, ,~ << 5L z* 9 I '$*>*> > LOzz/*>>C(H$II$'J4>>JZZt%uvv '<+?$%tuu12 A .1= A .23!)Q,/ HIRK *K ,BLQZD[\J
E!E*j* "+T__!2C%C
%)
OOO488!.1779")%/&-0B&B 9 =G$Y%89PJDJJ 'o9 v $4$9$9"$=$4$9$9"$=%6%;%;B%?
r final_beam_scoresfinal_beam_tokensfinal_beam_indicesc
t | j | j z }
|Bt |t j
s(t |t r|g}t j | }t | j D ] \ } } | j | rt | j D ]\ }
| | j z |
z }|| j }|| }||| nd }|j d | z
}| j |||| ^ |j |
| j z }g }g }t j" |
| j z | j$ t j& }t |
D ] }| j || j z |dz | j z }|D cg c] } | j( D ] }| }} }t+ |d }t | j D ]v } |j- } | d } | d } | d } t | || j |z | z < |j/ | |j/ | | ||| j z | z < x |j1 j dz }!| t3 |!| n|!}"|j |
| j z |" }#t | dkD r%|d |j |
| j z |" }$nd }$|j3 j |j1 j k7 r | t5 d |#j7 | |$|$j7 d t t9 || D ]Q \ }\ }%}&|%|#|d || f< |$%t j |& |$|d t |& f< || |"k sE|d |#||| f< S t; |#||$d
S c c}} w ) Nr[ r_ r2 r; r c | d S Nr r- xs r z+BeamSearchScorer.finalize..p s
! r keyr r `pad_token_id` has to be defined sequencessequence_scoresrW ) rk rE r6 rI r& r* r, rF rm rH rC rA rQ rj ro newr5 rl r2 float32beamssortedpopappendrq minrJ fill_rn r )'r r r~ r r r rU rV rW rY r0 ru beam_hypindex_per_groupr{ final_score final_tokensr} r` sent_lengthsbest best_indices best_scoresibeam_hyps_in_batchbeamcandidate_beams sorted_hypsjbest_hyp_tuple
best_scorebest_hyp
best_indexsent_lengths_max sent_max_lendecodedindiceshypobest_idxs' r r zBeamSearchScorer.finalizeD s )T-A-AA
#J|U\\,R,, ,~ << 5L *34??)C n %OXzz/* $) #9
n!04??!B_!T / ? D D F ( 8 =I=U\. 9[_
, 2 22 69K K
\;Z_l m
n
n !}}Z$2L2L%LM kk*t/I/I"IRVR]R]ejerers z" MA!% T5I5I1IQQRUVZVjVjLj!k 4F bS[SaSa b4t bt bO b nEK4556
M!, !2 +A .
)!, +A .
CFx= T 7 7! ;a ?@ H% ##J/BL A : : :Q >?
M M( (++-224q8 A h,0GA( a (( )".3ll8.D?S]?*+A -.:1o<?*+ > $#. '
_ cs &O ) ?Fr r N)NNNr r NNNr )r! r" r# r$ r, r& r2 floatr rG strr rL propertyrS r' r( r* listdictr r) r r- r r r/ r/ | sV $V !$.3%& $(22 2 2
2 !s+
2 #2 2 SM2h ' ' ' <@FJ37 "#g
##g
&&g
%% g
&& g
uS%,,%6 78
g
uS$s)U\\%A BCg
u / /0g
g
g
c5<< g
` <@FJ37"#`
##`
!,,`
!++ `
" , , `
`
uS%,,%6 78`
uS$s)U\\%A BC`
u / /0`
`
u `
r r/ c J e Zd ZdZ d%dededee dej de de
e e f d ed
e
e fd Zed e fd
Zd Zd Z d&dej& dej( dej& dej& dej( de
e
eej* f de
e
eee ej* f de
ej& ded eej* fdZ d'dedej& dej( d ej( d ej& d ej& d e fd Z d&dej& d!ej( d"ej& d#ej& d
ede
e
eej* f de
e
eee ej* f de
ej& ded eej& fd$Zy)(ConstrainedBeamSearchScorera
[`BeamScorer`] implementing constrained beam search decoding.
Args:
batch_size (`int`):
Batch Size of `input_ids` for which standard beam search decoding is run in parallel.
num_beams (`int`):
Number of beams for beam search.
constraints (`list[Constraint]`):
A list of positive constraints represented as `Constraint` objects that must be fulfilled in the generation
output. For more information, the documentation of [`Constraint`] should be read.
device (`torch.device`):
Defines the device type (*e.g.*, `"cpu"` or `"cuda"`) on which this instance of `BeamSearchScorer` will be
allocated.
length_penalty (`float`, *optional*, defaults to 1.0):
Exponential penalty to the length that is used with beam-based generation. It is applied as an exponent to
the sequence length, which in turn is used to divide the score of the sequence. Since the score is the log
likelihood of the sequence (i.e. negative), `length_penalty` > 0.0 promotes longer sequences, while
`length_penalty` < 0.0 encourages shorter sequences.
do_early_stopping (`bool` or `str`, *optional*, defaults to `False`):
Controls the stopping condition for beam-based methods, like beam-search. It accepts the following values:
`True`, where the generation stops as soon as there are `num_beams` complete candidates; `False`, where an
heuristic is applied and the generation stops when is it very unlikely to find better candidates;
`"never"`, where the beam search procedure only stops when there cannot be better candidates (canonical
beam search algorithm).
num_beam_hyps_to_keep (`int`, *optional*, defaults to 1):
The number of beam hypotheses that shall be returned upon calling
[`~transformers.BeamSearchScorer.finalize`].
max_length (`int`, *optional*):
The maximum length of the sequence to be generated.
Nr0 r1 constraintsr2 r3 r4 r5 r c t j d || _ || _ || _ || _ || _ || _ d| _ t | D cg c]/ } t | j | j | j
| 1 c} | _ t j t | D cg c] } d c} t j | j | _ t! |t" r|dk rt% d| d y c c} w c c} w )Nz`ConstrainedBeamSearchScorer` is deprecated and will be removed in v4.62.0, as constrained beam search has been moved to the Hub: https://hf.co/transformers-community/constrained-beam-search.Fr8 r: r r< r= )r? r@ r1 r2 r3 r4 r5 r rB rC rD rE r& rF rG rH rI r, rJ )
r r0 r1 r r2 r3 r4 r5 r rK s
r rL z$ConstrainedBeamSearchScorer.__init__ s
N
# ,!2 %:"&
:&
.. # 2 2 # 5 5%
\\%
2C"DQ5"DEJJ_c_j_jk
)S)Y!^ ST]S^ _C C
.<
#Es 4D, Dr c R | j j j S rN rO rR s r rS z#ConstrainedBeamSearchScorer.is_done rT r c t | D cg c]3 }t | j D cg c] }|j c} 5 c}}S c c}w c c}}w rN )rC r
r copy)r nrK
constraints r make_constraint_statesz2ConstrainedBeamSearchScorer.make_constraint_states s> ejklemn`a#IYIY$Z:Z__%6$Z[nn$Zns AA A Ac d | j d d }|j | |j S )Nr r )r reset completed)r sequence new_states r check_completes_constraintsz7ConstrainedBeamSearchScorer.check_completes_constraints s/ //215 !"""r r r r r scores_for_all_vocabrU rV rW rY c
|j d dz }
t | j } |j } t j
| | j f|j | }
t j
| | j f|j | }t j
| | j f|j | }|Bt |t j s(t |t r|g}t j | }t | j D ]& \ }}| j | r\| j t | k rt d| j d || t d d|
|ddf< |||ddf< d||ddf< rd}t t || || || D ] \ }\ }}}|| j z |z }||j! |v r~|| j k\ }|rB| j# || j% }|rb| || }||fz }nd}|j' || j) |j! ||
| z
n||
||f< ||||f< ||||f< |dz
}|| j k( s n | j+ ||||
| || || \ }} } ||
|< | ||< | ||< || j k r(t d
| j d || d | d
|| d | j | xs2 |j- || j/ j! |
| | j |< ) t1 |
j3 d |j3 d |j3 d d S )al
Args:
input_ids (`torch.LongTensor` of shape `(batch_size * num_beams, sequence_length)`):
Indices of input sequence tokens in the vocabulary.
Indices can be obtained using any class inheriting from [`PreTrainedTokenizer`]. See
[`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details.
[What are input IDs?](../glossary#input-ids)
next_scores (`torch.FloatTensor` of shape `(batch_size, 2 * num_beams)`):
Current scores of the top `2 * num_beams` non-finished beam hypotheses.
next_tokens (`torch.LongTensor` of shape `(batch_size, 2 * num_beams)`):
`input_ids` of the tokens corresponding to the top `2 * num_beams` non-finished beam hypotheses.
next_indices (`torch.LongTensor` of shape `(batch_size, 2 * num_beams)`):
Beam indices indicating to which beam hypothesis the `next_tokens` correspond.
scores_for_all_vocab (`torch.FloatTensor` of shape `(batch_size * num_beams, sequence_length)`):
The scores of all tokens in the vocabulary for each of the beam hypotheses.
pad_token_id (`int`, *optional*):
The id of the *padding* token.
eos_token_id (`Union[int, list[int]]`, *optional*):
The id of the *end-of-sequence* token. Optionally, use a list to set multiple *end-of-sequence* tokens.
beam_indices (`torch.LongTensor`, *optional*):
Beam indices indicating to which beam hypothesis each token correspond.
decoder_prompt_len (`int`, *optional*):
The length of prompt that is included in the input to decoder.
Return:
`UserDict`: A dictionary composed of the fields as defined above:
- **next_beam_scores** (`torch.FloatTensor` of shape `(batch_size * num_beams)`) -- Updated scores of
all
non-finished beams.
- **next_beam_tokens** (`torch.FloatTensor` of shape `(batch_size * num_beams)`) -- Next tokens to be
added
to the non-finished beam_hypotheses.
- **next_beam_indices** (`torch.FloatTensor` of shape `(batch_size * num_beams)`) -- Beam indices
indicating to which beam the next tokens shall be added.
r[ r r: Nr\ r] r^ r r_ ra rb rc rd re rf )rj rk rE r2 r& rl r1 r; rI r* r, rF rm rH rJ rn rQ r tolistro rp step_sentence_constraintrS rq r rr ) r r r r r r rU rV rW rY rs r0 r2 rg rh ri rt r rv rw rx ry rz r{ r| completes_constraintr}
new_scores
new_tokens new_indicess r r z#ConstrainedBeamSearchScorer.process s h //"%) )
!! ;;
DNN'C;K\K\ekl ;;
DNN'C;K\K\ekl !KKT^^(DLL^L^gm n #J|U\\,R,, ,~ << 5L#,T__#= H Ixzz)$>>CM1$'J4>>JZZt%uvv '<+?$%tuu12 A .1= A .23!)Q,/ HIRK *K ,BLQZD[\J "
E!E*j* "+T^^!;j!H ,:??3D 3T=LPTP^P^=^:= +/+K+KIVdLeLlLlLn+o(+'3)5n)EJ)3~6G)GJ)-J %n 5 ; ; = &OO -)3*14F*F % =G$Y%89P>DJJy !MH T $4$9$9"$=$4$9$9"$=%6%;%;B%?
r rt vocab_scoressent_beam_scoressent_beam_tokenssent_beam_indices
push_progressc B |j d }|j } | j | }
| j | } ||z |dz |z }
} || |
}|| |
}t j || |j d fd }|j
g g g g d}t | D ]\ \ }}|
| }|j || j
| | }|j |j
|j s$t j |j t j | }|D ] }|j d }|j |j
t j ||j d fd j
}||d vsq|d j | |d
j | |z |d j | |d j || j! | |d
j | |st j" || d \ }}t j ||j d fd }| | }|j
}|j | ||d vs|d j | |d
j | |d j | |d j | |d
j | _ t% |d
dkD rt j |d
| } t j& |d j) | } t j& |d j) | } |
|d
z } t j || fd } t j || fd }!t j | D "cg c] }"|"j+ c}"| }#|#dz |!z }$|$j- d j. }%|#|% }&d}'|&d }(g })|&D ]" }*|*|(k( r|'dz
}'nd}'|*}(|)j |' $ t j t1 j2 |)d }+|%|+ d | }%|!|% }| |% }t j || f |% }|||fS c c}"w )Nr r r[ )dim)new_seqs
new_statesr r r r: T)statefulr r r r r )r2 d )
descending mergesort)kind)sizer2 r r& cat unsqueezer rm r r rF advancelongr ro r takerq rk stacktoget_banksortr npargsort),r rt r r r r r r orig_lenr2 topk_constraint_statesadvance_constraint_statessidxeidxthis_batch_input_idsthis_batch_token_scoresfull_hypotheses track_newseq_idxpre_seq
topk_state
advance_stateadvance_tokens
advance_tokenr advance_seq new_score new_tokenr r r
all_states
all_tokens
all_scoresone all_bankszippedr sorted_bankscountercur_bank
incrementsbank rearrangerss, r r z4ConstrainedBeamSearchScorer.step_sentence_constraint s ( %))!,")) "&! ? ? B GW 08J _W 5 < < > ? 5g >M 0 1 **!& m.C.C.EUZZ`f!g%3 BM - 2 2D 2 AI MM-"6"6"89"'))Wm6M6Ma6P,QSU"V"]"]"_K")J*??!*-44[A!-077wG!,/66}E!,/667Nw7W7\7\]j7kl!,/66yA B ( (-yy1H1QST'U$ 9 #ii)2E2Ea2H(I2 N 9' B
) 0 0 2 ##K0 i
&;; j)00= m,33G< l+229= l+229= l+22=A? BB y ' (1 , ,,y '?OK Y|%<=@@HJ Y|%<=@@HJ/)L2IIJ $4j#A2FJ $4j#A2FJ
%Kclln%KTZ[I _z1F kkTk2::G$W-L G#AHJ$
+8#qLG G #H!!'*
+ ,,rzz*;'OPK k*9H5G )' 2 )' 2 % +.Z s
qt r r r r r r r ) rk rE rI r& r* r, rF rm rH rC r1 rQ r r rj ro r r5 r rl r2 r r r r rq r rJ r rn r )&r r r~ r r r rU rV rW rY r0 rt r ids_collectbeam_idr{ r r r r} r` r r r r r r r r r r r r r r r r r s& r r z$ConstrainedBeamSearchScorer.finalize st )
#J|U\\,R,, ,~ << 5L $-T__#= Ixzz)$
K 0
0!*T^^!;g!E / ? D D F ( 8 '+'G'G H[H[H]'^$'AMAY n!=_cJ$0$6$6r$:=O$OM LL {cpLq &&w/
0 ; $"<"<< $T^^ 4 G k1)2T^^)Cg)M&7&G&L&L&N '0 '@ (4(:(:2(>AS(S
\;m \;'4+E+EE / D !}}Z$2L2L%LM kk*t/I/I"IRVR]R]ejerers %T__5 MKAx ^DK4556
M!, !2 +A .
)!, +A .
CFx= T 7 7! ;a ?@ H% ##J/BL A : : :Q >?
M M$ (++-224q8 A h,0GA( a (( )".3ll8.D?S]?*+A -.:1o<?*+ > $#. '
r )r Fr Nr )F)r! r" r# r$ r, r r r& r2 r r rG r r rL r rS r r r' r( r* r) r r r r- r r r r s N !$.3%&$(%% % *% %
%
% !s+% #% SM%N ' ' 'o# <@FJ37"#R
##R
&&R
%% R
&& R
$ / /
R
uS%,,%6 78R
uS$s)U\\%A BCR
u / /0R
R
u|| R
x $KEKE ##KE '' KE
++ KE **
KE !++KE KEh <@FJ37"#r
##r
!,,r
!++ r
" , , r
r
uS%,,%6 78r
uS$s)U\\%A BCr
u / /0r
r
u r
r r c
e Zd Z ddededeeef dee fdZ d Z
dde j d ed
ee j d ee fd Z
dd
edededefdZy)rD Nr1 r3 r9 r c t j d || _ || _ || _ || _ g | _ d| _ t | j t s| j t d yy)z7
Initialize n-best list of hypotheses.
z`BeamHypotheses` is deprecated and will be removed in v4.62.0, as constrained beam search has been moved to the Hub: https://hf.co/transformers-community/constrained-beam-search.g eANzWhen `do_early_stopping` is set to a string, `max_length` must be defined. Ensure it is passed to the BeamScorer class instance at initialization time.) r? r@ r3 r9 r r1 r worst_scorerI rG rJ )r r1 r3 r9 r s r rL zBeamHypotheses.__init__ s|
A
- ,$"
$--t4 9P E
:Q4r c , t | j S )z3
Number of hypotheses in the list.
)rk r rR s r __len__zBeamHypotheses.__len__ s 4:: r hyp sum_logprobsrW r` c
|||| j z z }n ||j d | j z z }t | | j k s|| j kD r| j
j
|||f t | | j kD rZt t | j
D cg c]
\ }\ }}}||f c}}} } | j
| d d = | d d | _ yt || j | _ yyc c}}}w )z3
Add a new hypothesis to the list.
Nr[ r r )
r3 rj rk r1 r r r r rm r )
r r r rW r` scoreidxsrK sorted_next_scoress
r ro zBeamHypotheses.add s $ M43F3F$FGE !CIIbMT5H5H$HIE t9t~~ %1A1A)A JJ uc< 8 94y4>>)%+IVZV`V`La,b,b.#y1aaX,b%c"JJ 1! 4Q 78#5a#8#; #&ud.>.>#? *B -cs 0D best_sum_logprobsrs rY r c t | | j k ry| j du ry| j du r&|||z
| j z z }| j |k\ }|S | j dkD r:| j
|k r t
d || j
|z
| j z z }n|||z
| j z z }| j |k\ }|S )z
If there are enough hypotheses and that none of the hypotheses being generated can become better than the worst
one in the heap, then we are done with this sentence.
FTg z3max_length is not larger than decoder prompt length)rk r1 r9 r3 r r rJ )r r rs rY highest_attainable_scorerets r rS zBeamHypotheses.is_done s t9t~~ % $ &
E
)'8GFX>CJ ""S(??&88$%Z[[% ;M)MRVReRe(ee )
,=J\@\aeatat?t+t(""&>>CJr rN )NN)r )r! r" r# r, r r rG r r rL r
r& r' ro rS r- r r rD rD s sw .3EJ4QT9EUcklocp, 48'+ @
@ @ u / /0 @
} @2" " "RU "^b "r rD )abcr r collectionsr typingr r numpyr r& utilsr r
beam_constraintsr r
get_loggerr! r? r% r+ r r/ r rD r- r r r sz $ " 1 =
H % D 8 A A@h
z h
V h
* h
VX Xr