+
    œ°³jÁ  ã                   ó|   € ^ RI t ^ RIHt ^RIHt ^RIHt ^RIHt ]! RR7      ] ! R R	]4      4       4       t	R	.t
R# )
é    N)Ústrict)ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzopenbmb/MiniCPM3-4B)Ú
checkpointc                   ó0  a a€ ] tR t^t oRtRtR.tRRRRRRR	RR
RRRRRRR/tRR.R.3RRR.R.3RR.R.3/tRt	Rt
Rt^>t^(t^(tRtRtRtRtRtRt^t^t^tRtRtRtR tRtRtR!tR"t^@t ^ t!Rt"^t#R#t$R!t%V 3R$ lt&R% t'](V3R& lR' l4       t)V3R( lt*R)t+Vt,V ;t-# )*ÚMiniCPM3Configa  
kv_lora_rank (`int`, *optional*, defaults to 256):
    Rank of the low-rank KV projection in multi-head latent attention.
q_lora_rank (`int`, *optional*, defaults to 768):
    Rank of the low-rank query projection in multi-head latent attention. If `None`, the query projection
    is a single dense projection rather than a low-rank one.
qk_nope_head_dim (`int`, *optional*, defaults to 64):
    Dimension of the non-RoPE part of each query/key head.
qk_rope_head_dim (`int`, *optional*, defaults to 32):
    Dimension of the RoPE part of each query/key head.
v_head_dim (`int`, *optional*):
    Dimension of each value head. If `None`, defaults to `hidden_size // num_attention_heads`.
scale_emb (`int` or `float`, *optional*, defaults to 12):
    Multiplier applied to input embeddings.
scale_depth (`int` or `float`, *optional*, defaults to 1.4):
    Multiplier for residual connections; the effective scaling is `scale_depth / sqrt(num_hidden_layers)`.
    If `None`, defaults to `sqrt(num_hidden_layers)` (no-op scaling).
dim_model_base (`int`, *optional*, defaults to 256):
    Base model dimension used to scale logits before the language model head. If `None`,
    defaults to `hidden_size` (no-op scaling).

Example:

```python
>>> from transformers import MiniCPM3Model, MiniCPM3Config
>>> # Initializing a MiniCPM3 style configuration
>>> configuration = MiniCPM3Config()
>>> # Initializing a model from the configuration
>>> model = MiniCPM3Model(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```
Úminicpm3Úpast_key_valueszlayers.*.self_attn.q_projÚcolwisezlayers.*.self_attn.q_b_projz%layers.*.self_attn.kv_a_proj_with_mqaÚmla_kv_a_projzlayers.*.self_attn.kv_b_projzlayers.*.self_attn.o_projÚrowwisezlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projÚembed_tokensÚ	input_idsÚinputs_embedsÚlayersÚhidden_statesÚattention_maskÚnormiè i 
  i   Úsilui €  gš™™™™™¹?gñhãˆµøä>TNFg        é   i   gffffffö?c                ó0  <€ V P                   V n        V P                  V P                   ,           V n        V P                  f#   V P
                  V P                  ,          V n        V P                  f&   \        P                  ! V P                  4      V n        V P                  f   V P
                  V n        V P                  f#   V P
                  V P                  ,          V n        V P                  f   V P                  V n        \        SV `8  ! R/ VB  R # )N© )Úqk_rope_head_dimÚhead_dimÚqk_nope_head_dimÚqk_head_dimÚ
v_head_dimÚhidden_sizeÚnum_attention_headsÚscale_depthÚmathÚsqrtÚnum_hidden_layersÚdim_model_baseÚnum_key_value_headsÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s   &,€Út/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/minicpm3/configuration_minicpm3.pyr(   ÚMiniCPM3Config.__post_init__v   sÖ   ø€ à×-Ñ-ˆŒà×0Ñ0°4×3HÑ3HÕHˆÔð �?‰?Ò"Ø"×.Ñ.°$×2JÑ2JÕJˆDŒOØ×ÑÒ#Ü#Ÿyšy¨×)?Ñ)?Ó@ˆDÔØ×ÑÒ&Ø"&×"2Ñ"2ˆDÔØ�=‰=Ò Ø ×,Ñ,°×0HÑ0HÕHˆDŒMØ×#Ñ#Ò+Ø'+×'?Ñ'?ˆDÔ$ä‰ÒÑ' Ô'ó    c                ó–   € V P                   V P                  ,          ^ 8w  d'   \        RV P                    RV P                   R24      hR# )zOPart of `@strict`-powered validation. Validates the architecture of the config.zThe hidden size (z6) is not a multiple of the number of attention heads (z).N)r   r    Ú
ValueError©r)   s   &r,   Úvalidate_architectureÚ$MiniCPM3Config.validate_architectureŠ   sS   € à×Ñ˜d×6Ñ6Õ6¸!Ô;ÜØ# D×$4Ñ$4Ð#5ð 6Ø×2Ñ2Ð3°2ð7óð ñ <r.   c                ó    <€ V ^8„  d   QhRS[ /# )é   Úreturn)Úfloat)ÚformatÚ__classdict__s   "€r,   Ú__annotate__ÚMiniCPM3Config.__annotate__“   s   ø€ ÷ 6ñ 6¡ñ 6r.   c                ó<   € V P                   V P                  ,          # )N)r   r%   r1   s   &r,   Úlogits_scalingÚMiniCPM3Config.logits_scaling’   s   € ð ×Ñ $×"5Ñ"5Õ5Ð5r.   c                ó~  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R&   S[;R&   S[ ;R	&   S[;R
&   S[;R&   S[;R&   S[ R,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[ R,          ;R&   S[;R&   S[S[,          R,          ;R&   S[;R&   S[ S[,          R,          ;R&   S[;R&   S[ R,          ;R&   S[ ;R&   S[ R,          ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R&   S[ S[,          ;R&   S[ S[,          R,          ;R&   S[ R,          ;R&   # )r5   Ú
vocab_sizer   Úintermediate_sizer$   r    Nr&   Ú
hidden_actÚmax_position_embeddingsÚinitializer_rangeÚrms_norm_epsÚ	use_cacheÚpad_token_idÚbos_token_idÚeos_token_idÚpretraining_tpÚtie_word_embeddingsÚrope_parametersÚattention_biasÚattention_dropoutÚmlp_biasr   Úkv_lora_rankÚq_lora_rankr   r   r   Ú	scale_embr!   r%   )ÚintÚstrr7   ÚboolÚlistr   Údict)r8   r9   s   "€r,   r:   r;      s  ø‡ ‚ ñt Ññu ñv Ññw ñx Ñ!ñy ñz Ññ{ ñ| Ñ!ñ} ñ~ ˜t�Ñ(ñ ñ@ ÑñA ñB !Ñ(ñC ñD Ñ"ñE ñF ÑñG ñH ÑñI ñJ ˜•*Ñ#ñK ñL ˜•*Ñ ñM ñN ™™S�	•/ DÕ(Ñ,ñO ñP ˜$•JÑ"ñQ ñR Ñ$ñS ñT $¡dÕ*¨TÕ1Ñ8ñU ñV Ñ ñW ñX ™U•{ TÕ)Ñ/ñY ñZ Ññ[ ñ\ �D�jÑñ] ñ^ Ññ_ ñ` �t•Ñ!ña ñb Ññc ñd Ññe ñf �d•
Ñ!ñg ñh ‘U�{Ññi ñj ‘u•˜tÕ#Ñ)ñk ñl ˜$•JÑ$òm r.   )r%   r   r&   r   r!   r   ).Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planr@   r   rA   r$   r    r&   rB   rC   rD   rE   rF   rG   rH   rI   rJ   rK   rL   rM   rN   rO   r   rP   rQ   r   r   r   rR   r!   r%   r(   r2   Úpropertyr=   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r+   r9   s   @@r,   r	   r	      sL  ù‡ € ñ ðD €JØ#4Ð"5Ðð 	$ YØ% yØ/°Ø&¨	Ø# YØ  )Ø 	Ø  )ð	Ðð 	˜+˜¨Ð(9Ð:Ø�OÐ%5Ð6¸Ð8IÐJØ�/Ð" _Ð$5Ð6ðÐð €JØ€KØ!ÐØÐØ!ÐØ&(ÐØ€JØ#(ÐØ"ÐØ€LØ€IØ#€LØ €LØ+,€LØ!"€NØ $ÐØ48€OØ €NØ,/ÐØ€HØ€HØ€LØ!€KØÐØÐØ!€JØ€IØ&)€KØ!$€Nõ(ò(ð ÷6ó ð6÷k … r.   r	   )r"   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r	   Ú__all__r   r.   r,   Ú<module>rk      sN   ðó* å .å 3Ý 1Ý #ñ Ð0Ô1Øôu6Ð%ó u6ó ó 2ðu6ðp Ð
‚r.   