+
j R t ^ RIHt ^RIHt ^RIHt ]! RR7 ] ! R R]4 4 4 t]! RR7 ] ! R R ]4 4 4 t]! RR7 ] ! R
R ]4 4 4 t . R
Ot
R # )zIdefics model configuration)strict)PreTrainedConfig)auto_docstringzHuggingFaceM4/idefics-9b)
checkpointc h a ] tR t^t o RtRR/tRt^tRt^t ^ t
^t ^t Rt
RtRtR tR
tV 3R ltR tV tR
# )IdeficsVisionConfigidefics_vision hidden_size embed_dimi i gelugh㈵> {Gz?g ?c F < V ^8 d Qh/ S[ ;R& S[ S[S[ , , S[S[ S[ 3, , ;R& S[ ;R& S[ S[S[ , , S[S[ S[ 3, , ;R& S[ ;R& S[ ;R& S[ ;R& S[;R& S[;R & S[S[ , ;R
& S[;R & S[;R & # )
r
image_sizeintermediate_size
patch_sizenum_hidden_layersnum_attention_heads num_channels
hidden_actlayer_norm_epsattention_dropoutinitializer_rangeinitializer_factor)intlisttuplestrfloat)format
__classdict__s "r/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/idefics/configuration_idefics.py __annotate__ IdeficsVisionConfig.__annotate__ s
d3i%S/17 ! d3i%S/16 ! s{( #! " ## N)__name__
__module__ __qualname____firstlineno__
model_type
attribute_mapr
r r r r r r r r r r r __annotate_func____static_attributes____classdictcell__r! s @r" r r s_ "J"K0MI47J !46J !L J N%( # ## r% r c L a ] tR t^/t o RtRtRt^@t^t^t ^`t
Rt V 3R lt Rt
V tR# )IdeficsPerceiverConfiga
use_resampler (`bool`, *optional*, defaults to `False`):
Whether or not to use the resampler
resampler_n_latents (`int`, *optional*, defaults to 64):
Number of latent embeddings to resample ("compress") the input sequence to (usually < 128).
resampler_depth (`int`, *optional*, defaults to 6):
Depth of the Perceiver Resampler (Transformer w/ cross attention). Should be shallow (< 3).
resampler_n_heads (`int`, *optional*, defaults to 16):
Number of heads in each Transformer block (for multi-headed self-attention).
resampler_head_dim (`int`, *optional*, defaults to 96):
Dimensionality of each head projection in the Transformer block.
qk_layer_norms_perceiver (`bool`, *optional*, defaults to `False`):
Whether or not to use qk layer norms in perceiver
idefics_percieverFc b < V ^8 d Qh/ S[ ;R& S[;R& S[;R& S[;R& S[;R& S[ ;R& # )r
use_resamplerresampler_n_latentsresampler_depthresampler_n_headsresampler_head_dimqk_layer_norms_perceiver)boolr )r r! s "r" r# #IdeficsPerceiverConfig.__annotate__/ sS ( ) * !+ , - . / 0 1 2 #*3 r% r& N)r' r( r) r* __doc__r+ r5 r6 r7 r8 r9 r: r- r. r/ r0 s @r" r2 r2 / s:
%J M ! O %* 3 r% r2 c a a ] tR t^Kt oRtRtR]R]/tRt ^ t
Rt Rt ^ t
^ tRtR tR
tR tRtR tR
tRt^ t^t^tRt^tRt Rt Rt Rt Rt Rt!Rt"Rt#Rt$Rt%Rt&V 3R lt'V3R lt(Rt)Vt*V ;t+# )
IdeficsConfiga
additional_vocab_size (`int`, *optional*, defaults to 0):
Additional vocabulary size of the model, typically for the special "![]()
" token. Additional vocab tokens
are always trainable whereas regular vocab tokens can be frozen or not.
alpha_initializer (`str`, *optional*, defaults to `"zeros"`):
Initialization type for the alphas.
alphas_initializer_range (`float`, *optional*, defaults to 0.0):
The standard deviation of the truncated_normal_initializer for initializing the alphas in the Gated Cross
Attention.
alpha_type (`str`, *optional*, defaults to `"float"`):
Whether the gating alphas should be vectors or single floats.
cross_layer_interval (`int`, *optional*, default to 1):
Interval for cross attention (from text to image) layers.
qk_layer_norms (`bool`, *optional*, defaults to `False`):
Whether to add layer norm after q and k
freeze_text_layers (`bool`, *optional*, defaults to `True`):
Whether to freeze text layers
freeze_text_module_exceptions (`bool`, *optional*, defaults to `[]`):
Exceptions to freezing text layers when `freeze_text_layers` is `True`
freeze_lm_head (`bool`, *optional*, defaults to `False`):
Whether to freeze lm head
freeze_vision_layers (`bool`, *optional*, defaults to `True`):
Whether to freeze vision layers
freeze_vision_module_exceptions (`bool`, *optional*, defaults to `[]`):
Exceptions to freezing vision layers when `freeze_vision_layers` is `True`
use_resampler (`bool`, *optional*, defaults to `False`):
Whether to use the Resampler
perceiver_config (`IdeficsPerceiverConfig`, *optional*):
Custom perceiver config or dict
Example:
```python
>>> from transformers import IdeficsModel, IdeficsConfig
>>> # Initializing a Idefics idefics-9b style configuration
>>> configuration = IdeficsConfig()
>>> # Initializing a model from the idefics-9b style configuration
>>> model = IdeficsModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```ideficsperceiver_config
vision_configi } i i + r silur
zerosr gư>TFNi c < V P f \ 4 V n M:\ V P \ 4 ' d \ R/ V P B V n V P f \ 4 V n M:\ V P \ 4 ' d \ R/ V P B V n \ SV ` ! R/ VB R # )Nr& )rA r2
isinstancedictrB r super
__post_init__)selfkwargs __class__s &,r" rI IdeficsConfig.__post_init__ s ($:$rk s & " . 3 # 56$* $ 7$$ 56+ - + 7+4 56[($ [( 7[(| Mr%