fThSSSKJrJrJrJrJrJr SSKrSSK r SSK r SSK J r SSK J r Jr SSKJr SSKJr SSKJrJr SS KJr S S KJrJrJrJrJr S S KJr \(aSS K J!r! SS0r"Sr#\RH"\%5r&"SS\5r'"SS\\5r("SS\ RR5r*"SS\5r+"SS\5r,"SS\5r-"SS\5r."SS \5r//S!Qr0g)") TYPE_CHECKINGAnyDictListOptionalUnionN)nn)Cache DynamicCache)PretrainedConfig)BaseModelOutputWithPast) AddedTokenPreTrainedTokenizer)logging)LlamaForCausalLMLlamaForSequenceClassificationLlamaForTokenClassificationLlamaMLP LlamaModel)LlamaTokenizer) TextInput vocab_fileztokenizer.modelu▁c^\rSrSrSrSrS/rSSSSSSSS.rS/S /4S S /S /4S /S /4S .rSU4S jjr Sr U=r $) GemmaConfig1a This is the configuration class to store the configuration of a [`GemmaModel`]. It is used to instantiate an Gemma model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the Gemma-7B. e.g. [google/gemma-7b](https://huggingface.co/google/gemma-7b) Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 256000): Vocabulary size of the Gemma model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`GemmaModel`] hidden_size (`int`, *optional*, defaults to 3072): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 24576): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 28): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*, defaults to 16): This is the number of key_value heads that should be used to implement Grouped Query Attention. If `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details checkout [this paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `num_attention_heads`. head_dim (`int`, *optional*, defaults to 256): The attention head dimension. hidden_act (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`): The legacy activation function. It is overwritten by the `hidden_activation`. hidden_activation (`str` or `function`, *optional*): The non-linear activation function (function or string) in the decoder. Will default to `"gelu_pytorch_tanh"` if not specified. `"gelu_pytorch_tanh"` uses an approximation of the `"gelu"` activation function. max_position_embeddings (`int`, *optional*, defaults to 8192): The maximum sequence length that this model might ever be used with. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. rms_norm_eps (`float`, *optional*, defaults to 1e-06): The epsilon used by the rms normalization layers. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. pad_token_id (`int`, *optional*, defaults to 0): Padding token id. eos_token_id (`int`, *optional*, defaults to 1): End of stream token id. bos_token_id (`int`, *optional*, defaults to 2): Beginning of stream token id. tie_word_embeddings (`bool`, *optional*, defaults to `True`): Whether to tie weight embeddings rope_theta (`float`, *optional*, defaults to 10000.0): The base period of the RoPE embeddings. attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`): Whether to use a bias in the query, key, value and output projection layers during self-attention. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. ```python >>> from transformers import GemmaModel, GemmaConfig >>> # Initializing a Gemma gemma-7b style configuration >>> configuration = GemmaConfig() >>> # Initializing a model from the gemma-7b style configuration >>> model = GemmaModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```gemmapast_key_valuescolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_proj input_ids inputs_embeds hidden_statesattention_mask) embed_tokenslayersnormc >XlXlX lX0lX@lXPlXplX`lXlXl Xl Xl Xl UUl UUlUUl[ TU]D"SUUUUS.UD6 g)N) pad_token_id bos_token_id eos_token_idtie_word_embeddings) vocab_sizemax_position_embeddings hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headshead_dimnum_key_value_heads hidden_acthidden_activationinitializer_range rms_norm_eps use_cache rope_thetaattention_biasattention_dropoutsuper__init__)selfr/r1r2r3r4r6r5r7r8r0r9r:r;r*r,r+r-r<r=r>kwargs __class__s _/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/gemma/modular_gemma.pyr@GemmaConfig.__init__s0%'>$&!2!2#6  #6 $!2!2("$,!2  %%% 3    )r=r>r5r7r8r1r9r2r0r4r3r6r:r<r;r/)ii i`rHgelu_pytorch_tanhNi g{Gz?ư>TrrTg@Fg) __name__ __module__ __qualname____firstlineno____doc__ model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr@__static_attributes__ __classcell__rCs@rDrr1sA FJ#4"5%.%.%.%."+ )"+&(9:#%568IJ!"_$56& $ +/ / rFrc \rSrSrSrSS\\\\44Sjjr Sr Sr SS S \ \4S jr S rSS \ \S\S\S \4SjjrSrSrg)GemmaTokenizeraa Construct a Gemma tokenizer. Based on byte-level Byte-Pair-Encoding. The default padding token is unset as there is no padding token in the original model. Args: vocab_file (`str`): Path to the vocabulary file. unk_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `""`): The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead. bos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `""`): The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token. eos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `""`): The end of sequence token. pad_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `""`): A special token used to make arrays of tokens the same size for batching purpose. Will then be ignored by attention mechanisms or loss computation. sp_model_kwargs (`Dict[str, Any]`, `Optional`, *optional*): Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things, to set: - `enable_sampling`: Enable subword regularization. - `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout. - `nbest_size = {0,1}`: No sampling is performed. - `nbest_size > 1`: samples from the nbest_size results. - `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice) using forward-filtering-and-backward-sampling algorithm. - `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for BPE-dropout. add_bos_token (`bool`, *optional*, defaults to `True`): Whether or not to add an `bos_token` at the start of sequences. add_eos_token (`bool`, *optional*, defaults to `False`): Whether or not to add an `eos_token` at the end of sequences. clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`): Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like extra spaces. use_default_system_prompt (`bool`, *optional*, defaults to `False`): Whether or not the default system prompt for Gemma should be used. spaces_between_special_tokens (`bool`, *optional*, defaults to `False`): Whether or not to add spaces between special tokens. Nsp_model_kwargsc  Uc0OUUl[U[5(a [USSS9OUn[U[5(a [USSS9OUn[U[5(a [USSS9OUn[U[5(a [USSS9OUnXlXplXlXl[R"S0URD6Ul URRU5 [R"U4UUUUUUUU U U S. U D6 g)NFT) normalizedspecial) bos_token eos_token unk_token pad_token add_bos_token add_eos_tokenr\clean_up_tokenization_spacesuse_default_system_promptspaces_between_special_tokensr.)r\ isinstancestrrrrdrergspmSentencePieceProcessorsp_modelLoadrr@) rArrbr`rarcr\rdrerfrgrhrBs rDr@GemmaTokenizer.__init__s&5%URRU[S9$)zf Args: text: TextInput Returns a tokenized string. The Gemma tokenizer never adds a prefix space. )out_type)rmencoderjrs rD _tokenizeGemmaTokenizer._tokenize s }}##D3#77rF token_idsskip_special_tokensrhc (/n/nUHnU(aXpR;aMXpR;a]U(a*URURR U55 URURUR 5 /nMURU5 M U(a*URURR U55 U(aSR U5nOSR U5nUR[S5$)N ) all_special_ids_added_tokens_decoderappendrmdecodecontentjoinreplaceSPIECE_UNDERLINE)rArrrhrB sub_textscurrent_sub_textidss rD_decodeGemmaTokenizer._decode(s C"s.B.B'B000#$$T]]%9%9:J%KL  !;!;C!@!H!HI#%  '',    T]]112BC D (+I *I  !1377rFc/nSnUHGnX@R;a$X0RRU5U-- n/nM6URU5 MI X0RRU5- nU$)z:Converts a sequence of tokens (string) in a single string.r)_added_tokens_encoderrmrr)rAtokenscurrent_sub_tokens out_stringtokens rDconvert_tokens_to_string'GemmaTokenizer.convert_tokens_to_stringEst E222mm223EFNN %'""))%0  mm**+=>> rF)rdrermr\rgr) zzzzNTFFFF)FF)rMrNrOrPrQrrrjrr@ruryrr~rintboolrrrVr.rFrDrZrZs,b48%*"'&+) "$sCx.1) V55B[BtCyB8%*.3 898"8(, 8 8: rFrZcJ^\rSrSrS S\S\4U4SjjjrSrSrSr Sr U=r $) GemmaRMSNormiTdimepsc>[TU]5 X l[R"[ R "U55Ulg)N)r?r@rr Parametertorchzerosweight)rArrrCs rDr@GemmaRMSNorm.__init__Us, ll5;;s#34 rFcU[R"URS5RSSS9UR-5-$)NrT)keepdim)rrsqrtpowmeanr)rAxs rD_normGemmaRMSNorm._normZs45;;quuQx}}R}>IJJJrFcURUR55nUSURR5--nURU5$)Ng?)rfloatrtype_as)rAroutputs rDforwardGemmaRMSNorm.forward]sCAGGI&3!2!2!445~~a  rFc^[URR5SUR3$)Nz, eps=)tuplershaperrts rD extra_reprGemmaRMSNorm.extra_reprds' ))*+6$((<[TU]5 [R"URUR SS9Ul[R"URUR SS9Ul[R"UR URSS9Ulg)NF)bias) r?r@r Linearr1r2 gate_projup_proj down_proj)rAconfigrCs rDr@GemmaMLP.__init__isq 4#3#3T5K5KRWXyy!1!143I3IPUV 4#9#94;K;KRWXrF)rrr)rMrNrOrPr@rVrWrXs@rDrrhsYYrFrc\rSrSrSS\\R S\\RS\\R S\\\ \ \R4S\\RS\\ S \\ S \\ S \\R S \ 4S jjrSrg) GemmaModelipNr"r% position_idsrr#r;output_attentionsoutput_hidden_statescache_positionr|c dUbUOURRnUbUOURRnUbUOURRnUSLUSL- (a [ S5eUR (a/UR (aU(a[RS5 SnUcURU5nU(a Uc [5nU cDUbUR5OSn [R"XURS-URS9n UcU R!S5nUR#X%XU5n Un UR%X5n[R&"URR(S-U R*S9nX-n U(aS OSnU(aS OSnUR,SURR.H4nU(aUU 4- nU"U U UUUUU US 9nUSn U(dM+UUS4- nM6 UR1U 5n U(aUU 4- n[3U U(aUOSUUS 9$) Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.FrrL)deviceg?)dtyper.)r%rpast_key_valuerr;rposition_embeddings)last_hidden_staterr$ attentions)rrrr; ValueErrorgradient_checkpointingtraininglogger warning_oncer&r get_seq_lengthrarangerr unsqueeze_update_causal_mask rotary_embtensorr1rr'r3r(r)rAr"r%rrr#r;rrrrBpast_seen_tokens causal_maskr$r normalizerall_hidden_statesall_self_attns decoder_layer layer_outputss rDrGemmaModel.forwardqsI2C1N-TXT_T_TqTq$8$D $++JjJj "+!6IDKKL] & #oomJ \\$++"9"93">mFYFYZ %2 #7BD0d![[)H4;;+H+HIM#!m%55!)*)."3#-$7 M*!,M  =#3"55%J( -0  -!1 1 &+/8Od+%   rFr.) NNNNNNNNN)rMrNrOrPrr LongTensorTensorrr r FloatTensorrrrrVr.rFrDrrps151537KO59$(,0/359^ E,,-^ !.^ u//0 ^ "%tE4E4E/F(F"GH ^   1 12 ^ D>^ $D>^ 'tn^ !!1!12^  !^ ^ rFrc(^\rSrSrU4SjrSrU=r$)GemmaForCausalLMic 8>[5R"S0UD6$)a Example: ```python >>> from transformers import AutoTokenizer, GemmaForCausalLM >>> model = GemmaForCausalLM.from_pretrained("google/gemma-7b") >>> tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b") >>> prompt = "What is your favorite condiment?" >>> inputs = tokenizer(prompt, return_tensors="pt") >>> # Generate >>> generate_ids = model.generate(inputs.input_ids, max_length=30) >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] "What is your favorite condiment?" ```r.)r?r) super_kwargsrCs rDrGemmaForCausalLM.forwards$w...rFr.)rMrNrOrPrrVrWrXs@rDrrs //rFrc\rSrSrSrg)GemmaForSequenceClassificationir.NrMrNrOrPrVr.rFrDrrrFrc\rSrSrSrg)GemmaForTokenClassificationir.Nrr.rFrDrrrrFr)rrZrrrrGemmaPreTrainedModel)1typingrrrrrr sentencepiecerkrtorch.utils.checkpointr cache_utilsr r configuration_utilsr modeling_outputsrtokenization_utilsrrutilsrllama.modeling_llamarrrrrllama.tokenization_llamartokenization_utils_baserVOCAB_FILES_NAMESr get_loggerrMrrrZModulerrrrrr__all__r.rFrDrs CB .37A64!#45   H %D "D NY^%8Yx=299=(YxY_ _ D/'/, %C  "=  rF