relogic/pretrainkit/models/relationalsemparse/relational_semparse.py [207:427]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
          max_length=None,
          min_length=None,
          do_sample=None,
          early_stopping=None,
          num_beams=None,
          temperature=None,
          top_k=None,
          top_p=None,
          repetition_penalty=None,
          bad_words_ids=None,
          bos_token_id=None,
          pad_token_id=None,
          eos_token_id=None,
          length_penalty=None,
          no_repeat_ngram_size=None,
          num_return_sequences=None,
          attention_mask=None,
          decoder_start_token_id=None,
          use_cache=None,
          vocab_size=None,
          **model_specific_kwargs
    ):
        r""" Generates sequences for models with a LM head. The method currently supports greedy decoding, beam-search decoding, sampling with temperature, sampling with top-k or nucleus sampling.

        Adapted in part from `Facebook's XLM beam search code`_.

        .. _`Facebook's XLM beam search code`:
           https://github.com/facebookresearch/XLM/blob/9e6f6814d17be4fe5b15f2e6c43eb2b2d76daeb4/src/model/transformer.py#L529


        Parameters:

            input_ids: (`optional`) `torch.LongTensor` of shape `(batch_size, sequence_length)`
                The sequence used as a prompt for the generation. If `None` the method initializes
                it as an empty `torch.LongTensor` of shape `(1,)`.

            max_length: (`optional`) int
                The max length of the sequence to be generated.  Between `min_length` and infinity. Default to 20.

            min_length: (`optional`) int
                The min length of the sequence to be generated.  Between 0 and infinity. Default to 0.

            do_sample: (`optional`) bool
                If set to `False` greedy decoding is used. Otherwise sampling is used. Defaults to `False` as defined in `configuration_utils.PretrainedConfig`.

            early_stopping: (`optional`) bool
                if set to `True` beam search is stopped when at least `num_beams` sentences finished per batch. Defaults to `False` as defined in `configuration_utils.PretrainedConfig`.

            num_beams: (`optional`) int
                Number of beams for beam search. Must be between 1 and infinity. 1 means no beam search. Default to 1.

            temperature: (`optional`) float
                The value used to module the next token probabilities. Must be strictly positive. Default to 1.0.

            top_k: (`optional`) int
                The number of highest probability vocabulary tokens to keep for top-k-filtering. Between 1 and infinity. Default to 50.

            top_p: (`optional`) float
                The cumulative probability of parameter highest probability vocabulary tokens to keep for nucleus sampling. Must be between 0 and 1. Default to 1.

            repetition_penalty: (`optional`) float
                The parameter for repetition penalty. Between 1.0 and infinity. 1.0 means no penalty. Default to 1.0.

            pad_token_id: (`optional`) int
                Padding token. Default to specicic model pad_token_id or None if it does not exist.

            bos_token_id: (`optional`) int
                BOS token. Defaults to `bos_token_id` as defined in the models config.

            eos_token_id: (`optional`) int
                EOS token. Defaults to `eos_token_id` as defined in the models config.

            length_penalty: (`optional`) float
                Exponential penalty to the length. Default to 1.

            no_repeat_ngram_size: (`optional`) int
                If set to int > 0, all ngrams of size `no_repeat_ngram_size` can only occur once.
            bad_words_ids: (`optional`) list of lists of int
                `bad_words_ids` contains tokens that are not allowed to be generated. In order to get the tokens of the words that should not appear in the generated text, use `tokenizer.encode(bad_word, add_prefix_space=True)`.

            num_return_sequences: (`optional`) int
                The number of independently computed returned sequences for each element in the batch. Default to 1.

            attention_mask (`optional`) obj: `torch.LongTensor` of same shape as `input_ids`
                Mask to avoid performing attention on padding token indices.
                Mask values selected in ``[0, 1]``:
                ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
                Defaults to `None`.

                `What are attention masks? <../glossary.html#attention-mask>`__

            decoder_start_token_id=None: (`optional`) int
                If an encoder-decoder model starts decoding with a different token than BOS.
                Defaults to `None` and is changed to `BOS` later.

            use_cache: (`optional`) bool
                If `use_cache` is True, past key values are used to speed up decoding if applicable to model. Defaults to `True`.

            model_specific_kwargs: (`optional`) dict
                Additional model specific kwargs will be forwarded to the `forward` function of the model.

        Return:

            output: `torch.LongTensor` of shape `(batch_size * num_return_sequences, sequence_length)`
                sequence_length is either equal to max_length or shorter if all batches finished early due to the `eos_token_id`

        Examples::

            tokenizer = AutoTokenizer.from_pretrained('distilgpt2')   # Initialize tokenizer
            model = AutoModelWithLMHead.from_pretrained('distilgpt2')    # Download model and configuration from S3 and cache.
            outputs = model.generate(max_length=40)  # do greedy decoding
            print('Generated: {}'.format(tokenizer.decode(outputs[0], skip_special_tokens=True)))

            tokenizer = AutoTokenizer.from_pretrained('openai-gpt')   # Initialize tokenizer
            model = AutoModelWithLMHead.from_pretrained('openai-gpt')    # Download model and configuration from S3 and cache.
            input_context = 'The dog'
            input_ids = tokenizer.encode(input_context, return_tensors='pt')  # encode input context
            outputs = model.generate(input_ids=input_ids, num_beams=5, num_return_sequences=3, temperature=1.5)  # generate 3 independent sequences using beam search decoding (5 beams) with sampling from initial context 'The dog'
            for i in range(3): #  3 output sequences were generated
                print('Generated {}: {}'.format(i, tokenizer.decode(outputs[i], skip_special_tokens=True)))

            tokenizer = AutoTokenizer.from_pretrained('distilgpt2')   # Initialize tokenizer
            model = AutoModelWithLMHead.from_pretrained('distilgpt2')    # Download model and configuration from S3 and cache.
            input_context = 'The dog'
            input_ids = tokenizer.encode(input_context, return_tensors='pt')  # encode input context
            outputs = model.generate(input_ids=input_ids, max_length=40, temperature=0.7, num_return_sequences=3)  # 3 generate sequences using by sampling
            for i in range(3): #  3 output sequences were generated
                print('Generated {}: {}'.format(i, tokenizer.decode(outputs[i], skip_special_tokens=True)))

            tokenizer = AutoTokenizer.from_pretrained('ctrl')   # Initialize tokenizer
            model = AutoModelWithLMHead.from_pretrained('ctrl')    # Download model and configuration from S3 and cache.
            input_context = 'Legal My neighbor is'  # "Legal" is one of the control codes for ctrl
            input_ids = tokenizer.encode(input_context, return_tensors='pt')  # encode input context
            outputs = model.generate(input_ids=input_ids, max_length=50, temperature=0.7, repetition_penalty=1.2)  # generate sequences
            print('Generated: {}'.format(tokenizer.decode(outputs[0], skip_special_tokens=True)))

            tokenizer = AutoTokenizer.from_pretrained('gpt2')   # Initialize tokenizer
            model = AutoModelWithLMHead.from_pretrained('gpt2')    # Download model and configuration from S3 and cache.
            input_context = 'My cute dog'  # "Legal" is one of the control codes for ctrl
            bad_words_ids = [tokenizer.encode(bad_word, add_prefix_space=True) for bad_word in ['idiot', 'stupid', 'shut up']]
            input_ids = tokenizer.encode(input_context, return_tensors='pt')  # encode input context
            outputs = model.generate(input_ids=input_ids, max_length=100, do_sample=True, bad_words_ids=bad_words_ids)  # generate sequences without allowing bad_words to be generated
        """

        # We cannot generate if the model does not have a LM head
        if self.get_output_embeddings() is None:
            raise AttributeError(
                "You tried to generate sequences with a model that does not have a LM Head."
                "Please use another model class (e.g. `OpenAIGPTLMHeadModel`, `XLNetLMHeadModel`, `GPT2LMHeadModel`, `CTRLLMHeadModel`, `T5WithLMHeadModel`, `TransfoXLLMHeadModel`, `XLMWithLMHeadModel`, `BartForConditionalGeneration` )"
            )

        max_length = max_length if max_length is not None else self.config.max_length
        min_length = min_length if min_length is not None else self.config.min_length
        do_sample = do_sample if do_sample is not None else self.config.do_sample
        early_stopping = early_stopping if early_stopping is not None else self.config.early_stopping
        use_cache = use_cache if use_cache is not None else self.config.use_cache
        num_beams = num_beams if num_beams is not None else self.config.num_beams
        temperature = temperature if temperature is not None else self.config.temperature
        top_k = top_k if top_k is not None else self.config.top_k
        top_p = top_p if top_p is not None else self.config.top_p
        repetition_penalty = repetition_penalty if repetition_penalty is not None else self.config.repetition_penalty
        bos_token_id = bos_token_id if bos_token_id is not None else self.config.bos_token_id
        pad_token_id = pad_token_id if pad_token_id is not None else self.config.pad_token_id
        eos_token_id = eos_token_id if eos_token_id is not None else self.config.eos_token_id
        length_penalty = length_penalty if length_penalty is not None else self.config.length_penalty
        no_repeat_ngram_size = (
            no_repeat_ngram_size if no_repeat_ngram_size is not None else self.config.no_repeat_ngram_size
        )
        bad_words_ids = bad_words_ids if bad_words_ids is not None else self.config.bad_words_ids
        num_return_sequences = (
            num_return_sequences if num_return_sequences is not None else self.config.num_return_sequences
        )
        decoder_start_token_id = (
            decoder_start_token_id if decoder_start_token_id is not None else self.config.decoder_start_token_id
        )

        if input_ids is not None:
            batch_size = input_ids.shape[0]  # overriden by the input batch_size
        else:
            batch_size = 1

        assert isinstance(max_length, int) and max_length > 0, "`max_length` should be a strictly positive integer."
        assert isinstance(min_length, int) and min_length >= 0, "`min_length` should be a positive integer."
        assert isinstance(do_sample, bool), "`do_sample` should be a boolean."
        assert isinstance(early_stopping, bool), "`early_stopping` should be a boolean."
        assert isinstance(use_cache, bool), "`use_cache` should be a boolean."
        assert isinstance(num_beams, int) and num_beams > 0, "`num_beams` should be a strictly positive integer."
        assert temperature > 0, "`temperature` should be strictly positive."
        assert isinstance(top_k, int) and top_k >= 0, "`top_k` should be a positive integer."
        assert 0 <= top_p <= 1, "`top_p` should be between 0 and 1."
        assert repetition_penalty >= 1.0, "`repetition_penalty` should be >= 1."
        assert input_ids is not None or (
              isinstance(bos_token_id, int) and bos_token_id >= 0
        ), "If input_ids is not defined, `bos_token_id` should be a positive integer."
        assert pad_token_id is None or (
              isinstance(pad_token_id, int) and (pad_token_id >= 0)
        ), "`pad_token_id` should be a positive integer."
        assert (eos_token_id is None) or (
              isinstance(eos_token_id, int) and (eos_token_id >= 0)
        ), "`eos_token_id` should be a positive integer."
        assert length_penalty > 0, "`length_penalty` should be strictly positive."
        assert (
              isinstance(no_repeat_ngram_size, int) and no_repeat_ngram_size >= 0
        ), "`no_repeat_ngram_size` should be a positive integer."
        assert (
              isinstance(num_return_sequences, int) and num_return_sequences > 0
        ), "`num_return_sequences` should be a strictly positive integer."
        assert (
              bad_words_ids is None or isinstance(bad_words_ids, list) and isinstance(bad_words_ids[0], list)
        ), "`bad_words_ids` is either `None` or a list of lists of tokens that should not be generated"

        if input_ids is None:
            assert isinstance(bos_token_id, int) and bos_token_id >= 0, (
                "you should either supply a context to complete as `input_ids` input "
                "or a `bos_token_id` (integer >= 0) as a first token to start the generation."
            )
            input_ids = torch.full(
                (batch_size, 1), bos_token_id, dtype=torch.long, device=next(self.parameters()).device,
            )
        else:
            assert input_ids.dim() == 2, "Input prompt should be of shape (batch_size, sequence length)."
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



relogic/pretrainkit/models/semparse/semparse.py [214:434]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
          max_length=None,
          min_length=None,
          do_sample=None,
          early_stopping=None,
          num_beams=None,
          temperature=None,
          top_k=None,
          top_p=None,
          repetition_penalty=None,
          bad_words_ids=None,
          bos_token_id=None,
          pad_token_id=None,
          eos_token_id=None,
          length_penalty=None,
          no_repeat_ngram_size=None,
          num_return_sequences=None,
          attention_mask=None,
          decoder_start_token_id=None,
          use_cache=None,
          vocab_size=None,
          **model_specific_kwargs
    ):
        r""" Generates sequences for models with a LM head. The method currently supports greedy decoding, beam-search decoding, sampling with temperature, sampling with top-k or nucleus sampling.

        Adapted in part from `Facebook's XLM beam search code`_.

        .. _`Facebook's XLM beam search code`:
           https://github.com/facebookresearch/XLM/blob/9e6f6814d17be4fe5b15f2e6c43eb2b2d76daeb4/src/model/transformer.py#L529


        Parameters:

            input_ids: (`optional`) `torch.LongTensor` of shape `(batch_size, sequence_length)`
                The sequence used as a prompt for the generation. If `None` the method initializes
                it as an empty `torch.LongTensor` of shape `(1,)`.

            max_length: (`optional`) int
                The max length of the sequence to be generated.  Between `min_length` and infinity. Default to 20.

            min_length: (`optional`) int
                The min length of the sequence to be generated.  Between 0 and infinity. Default to 0.

            do_sample: (`optional`) bool
                If set to `False` greedy decoding is used. Otherwise sampling is used. Defaults to `False` as defined in `configuration_utils.PretrainedConfig`.

            early_stopping: (`optional`) bool
                if set to `True` beam search is stopped when at least `num_beams` sentences finished per batch. Defaults to `False` as defined in `configuration_utils.PretrainedConfig`.

            num_beams: (`optional`) int
                Number of beams for beam search. Must be between 1 and infinity. 1 means no beam search. Default to 1.

            temperature: (`optional`) float
                The value used to module the next token probabilities. Must be strictly positive. Default to 1.0.

            top_k: (`optional`) int
                The number of highest probability vocabulary tokens to keep for top-k-filtering. Between 1 and infinity. Default to 50.

            top_p: (`optional`) float
                The cumulative probability of parameter highest probability vocabulary tokens to keep for nucleus sampling. Must be between 0 and 1. Default to 1.

            repetition_penalty: (`optional`) float
                The parameter for repetition penalty. Between 1.0 and infinity. 1.0 means no penalty. Default to 1.0.

            pad_token_id: (`optional`) int
                Padding token. Default to specicic model pad_token_id or None if it does not exist.

            bos_token_id: (`optional`) int
                BOS token. Defaults to `bos_token_id` as defined in the models config.

            eos_token_id: (`optional`) int
                EOS token. Defaults to `eos_token_id` as defined in the models config.

            length_penalty: (`optional`) float
                Exponential penalty to the length. Default to 1.

            no_repeat_ngram_size: (`optional`) int
                If set to int > 0, all ngrams of size `no_repeat_ngram_size` can only occur once.
            bad_words_ids: (`optional`) list of lists of int
                `bad_words_ids` contains tokens that are not allowed to be generated. In order to get the tokens of the words that should not appear in the generated text, use `tokenizer.encode(bad_word, add_prefix_space=True)`.

            num_return_sequences: (`optional`) int
                The number of independently computed returned sequences for each element in the batch. Default to 1.

            attention_mask (`optional`) obj: `torch.LongTensor` of same shape as `input_ids`
                Mask to avoid performing attention on padding token indices.
                Mask values selected in ``[0, 1]``:
                ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
                Defaults to `None`.

                `What are attention masks? <../glossary.html#attention-mask>`__

            decoder_start_token_id=None: (`optional`) int
                If an encoder-decoder model starts decoding with a different token than BOS.
                Defaults to `None` and is changed to `BOS` later.

            use_cache: (`optional`) bool
                If `use_cache` is True, past key values are used to speed up decoding if applicable to model. Defaults to `True`.

            model_specific_kwargs: (`optional`) dict
                Additional model specific kwargs will be forwarded to the `forward` function of the model.

        Return:

            output: `torch.LongTensor` of shape `(batch_size * num_return_sequences, sequence_length)`
                sequence_length is either equal to max_length or shorter if all batches finished early due to the `eos_token_id`

        Examples::

            tokenizer = AutoTokenizer.from_pretrained('distilgpt2')   # Initialize tokenizer
            model = AutoModelWithLMHead.from_pretrained('distilgpt2')    # Download model and configuration from S3 and cache.
            outputs = model.generate(max_length=40)  # do greedy decoding
            print('Generated: {}'.format(tokenizer.decode(outputs[0], skip_special_tokens=True)))

            tokenizer = AutoTokenizer.from_pretrained('openai-gpt')   # Initialize tokenizer
            model = AutoModelWithLMHead.from_pretrained('openai-gpt')    # Download model and configuration from S3 and cache.
            input_context = 'The dog'
            input_ids = tokenizer.encode(input_context, return_tensors='pt')  # encode input context
            outputs = model.generate(input_ids=input_ids, num_beams=5, num_return_sequences=3, temperature=1.5)  # generate 3 independent sequences using beam search decoding (5 beams) with sampling from initial context 'The dog'
            for i in range(3): #  3 output sequences were generated
                print('Generated {}: {}'.format(i, tokenizer.decode(outputs[i], skip_special_tokens=True)))

            tokenizer = AutoTokenizer.from_pretrained('distilgpt2')   # Initialize tokenizer
            model = AutoModelWithLMHead.from_pretrained('distilgpt2')    # Download model and configuration from S3 and cache.
            input_context = 'The dog'
            input_ids = tokenizer.encode(input_context, return_tensors='pt')  # encode input context
            outputs = model.generate(input_ids=input_ids, max_length=40, temperature=0.7, num_return_sequences=3)  # 3 generate sequences using by sampling
            for i in range(3): #  3 output sequences were generated
                print('Generated {}: {}'.format(i, tokenizer.decode(outputs[i], skip_special_tokens=True)))

            tokenizer = AutoTokenizer.from_pretrained('ctrl')   # Initialize tokenizer
            model = AutoModelWithLMHead.from_pretrained('ctrl')    # Download model and configuration from S3 and cache.
            input_context = 'Legal My neighbor is'  # "Legal" is one of the control codes for ctrl
            input_ids = tokenizer.encode(input_context, return_tensors='pt')  # encode input context
            outputs = model.generate(input_ids=input_ids, max_length=50, temperature=0.7, repetition_penalty=1.2)  # generate sequences
            print('Generated: {}'.format(tokenizer.decode(outputs[0], skip_special_tokens=True)))

            tokenizer = AutoTokenizer.from_pretrained('gpt2')   # Initialize tokenizer
            model = AutoModelWithLMHead.from_pretrained('gpt2')    # Download model and configuration from S3 and cache.
            input_context = 'My cute dog'  # "Legal" is one of the control codes for ctrl
            bad_words_ids = [tokenizer.encode(bad_word, add_prefix_space=True) for bad_word in ['idiot', 'stupid', 'shut up']]
            input_ids = tokenizer.encode(input_context, return_tensors='pt')  # encode input context
            outputs = model.generate(input_ids=input_ids, max_length=100, do_sample=True, bad_words_ids=bad_words_ids)  # generate sequences without allowing bad_words to be generated
        """

        # We cannot generate if the model does not have a LM head
        if self.get_output_embeddings() is None:
            raise AttributeError(
                "You tried to generate sequences with a model that does not have a LM Head."
                "Please use another model class (e.g. `OpenAIGPTLMHeadModel`, `XLNetLMHeadModel`, `GPT2LMHeadModel`, `CTRLLMHeadModel`, `T5WithLMHeadModel`, `TransfoXLLMHeadModel`, `XLMWithLMHeadModel`, `BartForConditionalGeneration` )"
            )

        max_length = max_length if max_length is not None else self.config.max_length
        min_length = min_length if min_length is not None else self.config.min_length
        do_sample = do_sample if do_sample is not None else self.config.do_sample
        early_stopping = early_stopping if early_stopping is not None else self.config.early_stopping
        use_cache = use_cache if use_cache is not None else self.config.use_cache
        num_beams = num_beams if num_beams is not None else self.config.num_beams
        temperature = temperature if temperature is not None else self.config.temperature
        top_k = top_k if top_k is not None else self.config.top_k
        top_p = top_p if top_p is not None else self.config.top_p
        repetition_penalty = repetition_penalty if repetition_penalty is not None else self.config.repetition_penalty
        bos_token_id = bos_token_id if bos_token_id is not None else self.config.bos_token_id
        pad_token_id = pad_token_id if pad_token_id is not None else self.config.pad_token_id
        eos_token_id = eos_token_id if eos_token_id is not None else self.config.eos_token_id
        length_penalty = length_penalty if length_penalty is not None else self.config.length_penalty
        no_repeat_ngram_size = (
            no_repeat_ngram_size if no_repeat_ngram_size is not None else self.config.no_repeat_ngram_size
        )
        bad_words_ids = bad_words_ids if bad_words_ids is not None else self.config.bad_words_ids
        num_return_sequences = (
            num_return_sequences if num_return_sequences is not None else self.config.num_return_sequences
        )
        decoder_start_token_id = (
            decoder_start_token_id if decoder_start_token_id is not None else self.config.decoder_start_token_id
        )

        if input_ids is not None:
            batch_size = input_ids.shape[0]  # overriden by the input batch_size
        else:
            batch_size = 1

        assert isinstance(max_length, int) and max_length > 0, "`max_length` should be a strictly positive integer."
        assert isinstance(min_length, int) and min_length >= 0, "`min_length` should be a positive integer."
        assert isinstance(do_sample, bool), "`do_sample` should be a boolean."
        assert isinstance(early_stopping, bool), "`early_stopping` should be a boolean."
        assert isinstance(use_cache, bool), "`use_cache` should be a boolean."
        assert isinstance(num_beams, int) and num_beams > 0, "`num_beams` should be a strictly positive integer."
        assert temperature > 0, "`temperature` should be strictly positive."
        assert isinstance(top_k, int) and top_k >= 0, "`top_k` should be a positive integer."
        assert 0 <= top_p <= 1, "`top_p` should be between 0 and 1."
        assert repetition_penalty >= 1.0, "`repetition_penalty` should be >= 1."
        assert input_ids is not None or (
              isinstance(bos_token_id, int) and bos_token_id >= 0
        ), "If input_ids is not defined, `bos_token_id` should be a positive integer."
        assert pad_token_id is None or (
              isinstance(pad_token_id, int) and (pad_token_id >= 0)
        ), "`pad_token_id` should be a positive integer."
        assert (eos_token_id is None) or (
              isinstance(eos_token_id, int) and (eos_token_id >= 0)
        ), "`eos_token_id` should be a positive integer."
        assert length_penalty > 0, "`length_penalty` should be strictly positive."
        assert (
              isinstance(no_repeat_ngram_size, int) and no_repeat_ngram_size >= 0
        ), "`no_repeat_ngram_size` should be a positive integer."
        assert (
              isinstance(num_return_sequences, int) and num_return_sequences > 0
        ), "`num_return_sequences` should be a strictly positive integer."
        assert (
              bad_words_ids is None or isinstance(bad_words_ids, list) and isinstance(bad_words_ids[0], list)
        ), "`bad_words_ids` is either `None` or a list of lists of tokens that should not be generated"

        if input_ids is None:
            assert isinstance(bos_token_id, int) and bos_token_id >= 0, (
                "you should either supply a context to complete as `input_ids` input "
                "or a `bos_token_id` (integer >= 0) as a first token to start the generation."
            )
            input_ids = torch.full(
                (batch_size, 1), bos_token_id, dtype=torch.long, device=next(self.parameters()).device,
            )
        else:
            assert input_ids.dim() == 2, "Input prompt should be of shape (batch_size, sequence length)."
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -