# Blenderbot Small Note that [BlenderbotSmallModel](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallModel) and [BlenderbotSmallForConditionalGeneration](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallForConditionalGeneration) are only used in combination with the checkpoint [facebook/blenderbot-90M](https://huggingface.co/facebook/blenderbot-90M). Larger Blenderbot checkpoints should instead be used with [BlenderbotModel](/docs/transformers/main/en/model_doc/blenderbot#transformers.BlenderbotModel) and [BlenderbotForConditionalGeneration](/docs/transformers/main/en/model_doc/blenderbot#transformers.BlenderbotForConditionalGeneration) ## Overview The Blender chatbot model was proposed in [Recipes for building an open-domain chatbot](https://huggingface.co/papers/2004.13637) Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M. Smith, Y-Lan Boureau, Jason Weston on 30 Apr 2020. The abstract of the paper is the following: *Building open-domain chatbots is a challenging area for machine learning research. While prior work has shown that scaling neural models in the number of parameters and the size of the data they are trained on gives improved results, we show that other ingredients are important for a high-performing chatbot. Good conversation requires a number of skills that an expert conversationalist blends in a seamless way: providing engaging talking points and listening to their partners, and displaying knowledge, empathy and personality appropriately, while maintaining a consistent persona. We show that large scale models can learn these skills when given appropriate training data and choice of generation strategy. We build variants of these recipes with 90M, 2.7B and 9.4B parameter models, and make our models and code publicly available. Human evaluations show our best models are superior to existing approaches in multi-turn dialogue in terms of engagingness and humanness measurements. We then discuss the limitations of this work by analyzing failure cases of our models.* This model was contributed by [patrickvonplaten](https://huggingface.co/patrickvonplaten). The authors' code can be found [here](https://github.com/facebookresearch/ParlAI). ## Usage tips Blenderbot Small is a model with absolute position embeddings so it's usually advised to pad the inputs on the right rather than the left. ## Resources - [Causal language modeling task guide](../tasks/language_modeling) - [Translation task guide](../tasks/translation) - [Summarization task guide](../tasks/summarization) ## BlenderbotSmallConfig[[transformers.BlenderbotSmallConfig]] #### transformers.BlenderbotSmallConfig[[transformers.BlenderbotSmallConfig]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/blenderbot_small/configuration_blenderbot_small.py#L24) This is the configuration class to store the configuration of a Blenderbot SmallModel. It is used to instantiate a Blenderbot Small 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 [facebook/blenderbot_small-90M](https://huggingface.co/facebook/blenderbot_small-90M) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/main/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/main/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import BlenderbotSmallConfig, BlenderbotSmallModel >>> # Initializing a BlenderbotSmall facebook/blenderbot_small-90M style configuration >>> configuration = BlenderbotSmallConfig() >>> # Initializing a model (with random weights) from the facebook/blenderbot_small-90M style configuration >>> model = BlenderbotSmallModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** is_encoder_decoder (`bool`, *optional*, defaults to `True`) : Whether the model is used as an encoder/decoder or not. vocab_size (`int`, *optional*, defaults to `50265`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`. max_position_embeddings (`int`, *optional*, defaults to `512`) : The maximum sequence length that this model might ever be used with. encoder_layers (`int`, *optional*, defaults to `8`) : Number of hidden layers in the Transformer encoder. Will use the same value as `num_layers` if not set. encoder_ffn_dim (`int`, *optional*, defaults to `2048`) : Dimensionality of the "intermediate" (often named feed-forward) layer in encoder. encoder_attention_heads (`int`, *optional*, defaults to `16`) : Number of attention heads for each attention layer in the Transformer encoder. decoder_layers (`int`, *optional*, defaults to `8`) : Number of hidden layers in the Transformer decoder. Will use the same value as `num_layers` if not set. decoder_ffn_dim (`int`, *optional*, defaults to `2048`) : Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. decoder_attention_heads (`int`, *optional*, defaults to `16`) : Number of attention heads for each attention layer in the Transformer decoder. encoder_layerdrop (`Union[float, int]`, *optional*, defaults to `0.0`) : The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details. decoder_layerdrop (`Union[float, int]`, *optional*, defaults to `0.0`) : The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details. 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` or when the model is a decoder-only generative model. activation_function (`str`, *optional*, defaults to `gelu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc. d_model (`int`, *optional*, defaults to `512`) : Size of the encoder layers and the pooler layer. dropout (`Union[float, int]`, *optional*, defaults to `0.1`) : The ratio for all dropout layers. attention_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities. activation_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for activations inside the fully connected layer. init_std (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices. decoder_start_token_id (`int`, *optional*, defaults to `1`) : If an encoder-decoder model starts decoding with a different token than `bos`, the id of that token. scale_embedding (`bool`, *optional*, defaults to `False`) : Whether to scale embeddings by dividing by sqrt(d_model). pad_token_id (`int`, *optional*, defaults to `0`) : Token id used for padding in the vocabulary. bos_token_id (`int`, *optional*, defaults to `1`) : Token id used for beginning-of-stream in the vocabulary. eos_token_id (`Union[int, list[int]]`, *optional*, defaults to `2`) : Token id used for end-of-stream in the vocabulary. forced_eos_token_id (`Union[int, list[int]]`, *optional*, defaults to `2`) : The id of the token to force as the last generated token when `max_length` is reached. Usually set to `eos_token_id`. is_decoder (`bool`, *optional*, defaults to `False`) : Whether the model is used as a decoder or not. If `False`, the model is used as an encoder. tie_word_embeddings (`bool`, *optional*, defaults to `True`) : Whether to tie weight embeddings according to model's `tied_weights_keys` mapping. ## BlenderbotSmallTokenizer[[transformers.BlenderbotSmallTokenizer]] #### transformers.BlenderbotSmallTokenizer[[transformers.BlenderbotSmallTokenizer]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/blenderbot_small/tokenization_blenderbot_small.py#L51) Constructs a Blenderbot-90M tokenizer based on BPE (Byte-Pair-Encoding) This tokenizer inherits from [PreTrainedTokenizer](/docs/transformers/main/en/main_classes/tokenizer#transformers.PythonBackend) which contains most of the main methods. Users should refer to the superclass for more information regarding methods. get_special_tokens_masktransformers.BlenderbotSmallTokenizer.get_special_tokens_maskhttps://github.com/huggingface/transformers/blob/main/src/transformers/tokenization_python.py#L965[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": list | None = None"}, {"name": "already_has_special_tokens", "val": ": bool = False"}]- **token_ids_0** (`list[int]`) -- List of ids of the first sequence. - **token_ids_1** (`list[int]`, *optional*) -- List of ids of the second sequence. - **already_has_special_tokens** (`bool`, *optional*, defaults to `False`) -- Whether or not the token list is already formatted with special tokens for the model.0A list of integers in the range [0, 1]1 for a special token, 0 for a sequence token. Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer `prepare_for_model` or `encode_plus` methods. This method dynamically builds the special tokens mask based on the tokenizer's `special_tokens_pattern`: - `"none"`: No special tokens (default, returns all 0s) - `"cls_sep"`: [CLS] seq0 [SEP] or [CLS] seq0 [SEP] seq1 [SEP] - `"eos"`: seq0 [EOS] or seq0 [EOS] seq1 [EOS] - `"bos"`: [BOS] seq0 or [BOS] seq0 [BOS] seq1 - `"bos_eos"`: [BOS] seq0 [EOS] or [BOS] seq0 [EOS] seq1 [EOS] - `"cls_double_sep"`: [CLS] seq0 [SEP] or [CLS] seq0 [SEP] [SEP] seq1 [SEP] - `"prefix_suffix"`: ` seq0 [seq1] ` **Parameters:** vocab_file (`str`) : File containing the vocabulary. merges_file (`str`) : Path to the merges file. bos_token (`str`, *optional*, defaults to `"__start__"`) : The beginning of sentence token. eos_token (`str`, *optional*, defaults to `"__end__"`) : The end of sentence token. unk_token (`str`, *optional*, defaults to `"__unk__"`) : 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. pad_token (`str`, *optional*, defaults to `"__null__"`) : The token used for padding, for example when batching sequences of different lengths. kwargs (*optional*) : Additional keyword arguments passed along to [PreTrainedTokenizer](/docs/transformers/main/en/main_classes/tokenizer#transformers.PythonBackend) **Returns:** `A list of integers in the range [0, 1]` 1 for a special token, 0 for a sequence token. #### save_vocabulary[[transformers.BlenderbotSmallTokenizer.save_vocabulary]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/blenderbot_small/tokenization_blenderbot_small.py#L192) ## BlenderbotSmallTokenizerFast[[transformers.BlenderbotSmallTokenizer]] #### transformers.BlenderbotSmallTokenizer[[transformers.BlenderbotSmallTokenizer]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/blenderbot_small/tokenization_blenderbot_small.py#L51) Constructs a Blenderbot-90M tokenizer based on BPE (Byte-Pair-Encoding) This tokenizer inherits from [PreTrainedTokenizer](/docs/transformers/main/en/main_classes/tokenizer#transformers.PythonBackend) which contains most of the main methods. Users should refer to the superclass for more information regarding methods. convert_tokens_to_stringtransformers.BlenderbotSmallTokenizer.convert_tokens_to_stringhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/blenderbot_small/tokenization_blenderbot_small.py#L187[{"name": "tokens", "val": ": list"}] Converts a sequence of tokens in a single string. **Parameters:** vocab_file (`str`) : File containing the vocabulary. merges_file (`str`) : Path to the merges file. bos_token (`str`, *optional*, defaults to `"__start__"`) : The beginning of sentence token. eos_token (`str`, *optional*, defaults to `"__end__"`) : The end of sentence token. unk_token (`str`, *optional*, defaults to `"__unk__"`) : 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. pad_token (`str`, *optional*, defaults to `"__null__"`) : The token used for padding, for example when batching sequences of different lengths. kwargs (*optional*) : Additional keyword arguments passed along to [PreTrainedTokenizer](/docs/transformers/main/en/main_classes/tokenizer#transformers.PythonBackend) ## BlenderbotSmallModel[[transformers.BlenderbotSmallModel]] #### transformers.BlenderbotSmallModel[[transformers.BlenderbotSmallModel]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/blenderbot_small/modeling_blenderbot_small.py#L611) The bare Blenderbot Small Model outputting raw hidden-states without any specific head on top. This model inherits from [PreTrainedModel](/docs/transformers/main/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. forwardtransformers.BlenderbotSmallModel.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/blenderbot_small/modeling_blenderbot_small.py#L637[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.LongTensor | None = None"}, {"name": "encoder_outputs", "val": ": list[torch.FloatTensor] | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "decoder_inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/main/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **decoder_input_ids** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) -- Indices of decoder input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/main/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are decoder input IDs?](../glossary#decoder-input-ids) BlenderbotSmall uses the `bos_token_id` as the starting token for `decoder_input_ids` generation. If `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see `past_key_values`). - **decoder_attention_mask** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) -- Default behavior: generate a tensor that ignores pad tokens in `decoder_input_ids`. Causal mask will also be used by default. - **encoder_outputs** (`list[torch.FloatTensor]`, *optional*) -- Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`) `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. - **past_key_values** (`~cache_utils.Cache`, *optional*) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only [Cache](/docs/transformers/main/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, [DynamicCache](/docs/transformers/main/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. - **inputs_embeds** (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **decoder_inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded representation. If `past_key_values` is used, optionally only the last `decoder_inputs_embeds` have to be input (see `past_key_values`). This is useful if you want more control over how to convert `decoder_input_ids` indices into associated vectors than the model's internal embedding lookup matrix. If `decoder_input_ids` and `decoder_inputs_embeds` are both unset, `decoder_inputs_embeds` takes the value of `inputs_embeds`. - **use_cache** (`bool`, *optional*) -- If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`).0[Seq2SeqModelOutput](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or `tuple(torch.FloatTensor)`A [Seq2SeqModelOutput](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([BlenderbotSmallConfig](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallConfig)) and inputs. The [BlenderbotSmallModel](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallModel) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the decoder of the model. If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1, hidden_size)` is output. - **past_key_values** (`EncoderDecoderCache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [EncoderDecoderCache](/docs/transformers/main/en/internal/generation_utils#transformers.EncoderDecoderCache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. - **decoder_hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the decoder at the output of each layer plus the optional initial embedding outputs. - **decoder_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads. - **cross_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads. - **encoder_last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder of the model. - **encoder_hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the encoder at the output of each layer plus the optional initial embedding outputs. - **encoder_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads. Example: ```python >>> from transformers import AutoTokenizer, BlenderbotSmallModel >>> model = BlenderbotSmallModel.from_pretrained("facebook/blenderbot_small-90M") >>> tokenizer = AutoTokenizer.from_pretrained("facebook/blenderbot_small-90M") >>> inputs = tokenizer("Studies have been shown that owning a dog is good for you", return_tensors="pt") >>> decoder_inputs = tokenizer("Studies show that", return_tensors="pt") # Batch size 1 >>> outputs = model(input_ids=inputs.input_ids, decoder_input_ids=decoder_inputs.input_ids) >>> last_hidden_states = outputs.last_hidden_state >>> list(last_hidden_states.shape) [1, 3, 512] ``` **Parameters:** config ([BlenderbotSmallConfig](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/main/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[Seq2SeqModelOutput](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or `tuple(torch.FloatTensor)`` A [Seq2SeqModelOutput](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([BlenderbotSmallConfig](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallConfig)) and inputs. ## BlenderbotSmallForConditionalGeneration[[transformers.BlenderbotSmallForConditionalGeneration]] #### transformers.BlenderbotSmallForConditionalGeneration[[transformers.BlenderbotSmallForConditionalGeneration]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/blenderbot_small/modeling_blenderbot_small.py#L727) The BlenderbotSmall Model with a language modeling head. Can be used for summarization. This model inherits from [PreTrainedModel](/docs/transformers/main/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. forwardtransformers.BlenderbotSmallForConditionalGeneration.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/blenderbot_small/modeling_blenderbot_small.py#L759[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.LongTensor | None = None"}, {"name": "encoder_outputs", "val": ": list[torch.FloatTensor] | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "decoder_inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/main/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **decoder_input_ids** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) -- Indices of decoder input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/main/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are decoder input IDs?](../glossary#decoder-input-ids) BlenderbotSmall uses the `bos_token_id` as the starting token for `decoder_input_ids` generation. If `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see `past_key_values`). - **decoder_attention_mask** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) -- Default behavior: generate a tensor that ignores pad tokens in `decoder_input_ids`. Causal mask will also be used by default. - **encoder_outputs** (`list[torch.FloatTensor]`, *optional*) -- Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`) `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. - **past_key_values** (`~cache_utils.Cache`, *optional*) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only [Cache](/docs/transformers/main/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, [DynamicCache](/docs/transformers/main/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. - **inputs_embeds** (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **decoder_inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded representation. If `past_key_values` is used, optionally only the last `decoder_inputs_embeds` have to be input (see `past_key_values`). This is useful if you want more control over how to convert `decoder_input_ids` indices into associated vectors than the model's internal embedding lookup matrix. If `decoder_input_ids` and `decoder_inputs_embeds` are both unset, `decoder_inputs_embeds` takes the value of `inputs_embeds`. - **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Labels for computing the masked language modeling loss. Indices should either be in `[0, ..., config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`. - **use_cache** (`bool`, *optional*) -- If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`).0[Seq2SeqLMOutput](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or `tuple(torch.FloatTensor)`A [Seq2SeqLMOutput](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([BlenderbotSmallConfig](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallConfig)) and inputs. The [BlenderbotSmallForConditionalGeneration](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallForConditionalGeneration) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Language modeling loss. - **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - **past_key_values** (`EncoderDecoderCache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [EncoderDecoderCache](/docs/transformers/main/en/internal/generation_utils#transformers.EncoderDecoderCache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. - **decoder_hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the decoder at the output of each layer plus the initial embedding outputs. - **decoder_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads. - **cross_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads. - **encoder_last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder of the model. - **encoder_hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the encoder at the output of each layer plus the initial embedding outputs. - **encoder_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads. Example Conversation: ```python >>> from transformers import AutoTokenizer, BlenderbotSmallForConditionalGeneration >>> mname = "facebook/blenderbot_small-90M" >>> model = BlenderbotSmallForConditionalGeneration.from_pretrained(mname) >>> tokenizer = AutoTokenizer.from_pretrained(mname) >>> UTTERANCE = "My friends are cool but they eat too many carbs." >>> print("Human: ", UTTERANCE) Human: My friends are cool but they eat too many carbs. >>> inputs = tokenizer([UTTERANCE], return_tensors="pt") >>> reply_ids = model.generate(**inputs) >>> print("Bot: ", tokenizer.batch_decode(reply_ids, skip_special_tokens=True)[0]) Bot: what kind of carbs do they eat? i don't know much about carbs. >>> REPLY = "I'm not sure" >>> print("Human: ", REPLY) Human: I'm not sure >>> NEXT_UTTERANCE = ( ... "My friends are cool but they eat too many carbs.__end__ __start__what kind of carbs do they eat? " ... "i don't know much about carbs__end__ " ... "__start__ I'm not sure." ... ) >>> inputs = tokenizer([NEXT_UTTERANCE], return_tensors="pt") >>> next_reply_ids = model.generate(**inputs) >>> print("Bot: ", tokenizer.batch_decode(next_reply_ids, skip_special_tokens=True)[0]) Bot: they eat a lot of carbs. carbs are high in fat, protein, and fats. ``` **Parameters:** config ([BlenderbotSmallConfig](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/main/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[Seq2SeqLMOutput](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or `tuple(torch.FloatTensor)`` A [Seq2SeqLMOutput](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([BlenderbotSmallConfig](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallConfig)) and inputs. ## BlenderbotSmallForCausalLM[[transformers.BlenderbotSmallForCausalLM]] #### transformers.BlenderbotSmallForCausalLM[[transformers.BlenderbotSmallForCausalLM]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/blenderbot_small/modeling_blenderbot_small.py#L888) forwardtransformers.BlenderbotSmallForCausalLM.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/blenderbot_small/modeling_blenderbot_small.py#L910[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "encoder_hidden_states", "val": ": torch.FloatTensor | None = None"}, {"name": "encoder_attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "logits_to_keep", "val": ": int | torch.Tensor = 0"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/main/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **encoder_hidden_states** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder. - **encoder_attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. - **past_key_values** (`~cache_utils.Cache`, *optional*) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only [Cache](/docs/transformers/main/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, [DynamicCache](/docs/transformers/main/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Labels for computing the masked language modeling loss. Indices should either be in `[0, ..., config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`. - **use_cache** (`bool`, *optional*) -- If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`). - **logits_to_keep** (`Union[int, torch.Tensor]`, *optional*, defaults to `0`) -- If an `int`, compute logits for the last `logits_to_keep` tokens. If `0`, calculate logits for all `input_ids` (special case). Only last token logits are needed for generation, and calculating them only for that token can save memory, which becomes pretty significant for long sequences or large vocabulary size. If a `torch.Tensor`, must be 1D corresponding to the indices to keep in the sequence length dimension. This is useful when using packed tensor format (single dimension for batch and sequence length).0[CausalLMOutputWithCrossAttentions](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`A [CausalLMOutputWithCrossAttentions](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([BlenderbotSmallConfig](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallConfig)) and inputs. The [BlenderbotSmallForCausalLM](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallForCausalLM) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Language modeling loss (for next-token prediction). - **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. - **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. - **cross_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Cross attentions weights after the attention softmax, used to compute the weighted average in the cross-attention heads. - **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/main/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. Example: ```python >>> from transformers import AutoTokenizer, BlenderbotSmallForCausalLM >>> tokenizer = AutoTokenizer.from_pretrained("facebook/blenderbot_small-90M") >>> model = BlenderbotSmallForCausalLM.from_pretrained("facebook/blenderbot_small-90M") >>> assert model.config.is_decoder, f"{model.__class__} has to be configured as a decoder." >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> outputs = model(**inputs) >>> logits = outputs.logits >>> expected_shape = [1, inputs.input_ids.shape[-1], model.config.vocab_size] >>> list(logits.shape) == expected_shape True ``` **Parameters:** input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) : Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/main/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) : Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) : Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder. encoder_attention_mask (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) : Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. past_key_values (`~cache_utils.Cache`, *optional*) : Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only [Cache](/docs/transformers/main/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, [DynamicCache](/docs/transformers/main/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) : Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) : Labels for computing the masked language modeling loss. Indices should either be in `[0, ..., config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`. use_cache (`bool`, *optional*) : If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`). logits_to_keep (`Union[int, torch.Tensor]`, *optional*, defaults to `0`) : If an `int`, compute logits for the last `logits_to_keep` tokens. If `0`, calculate logits for all `input_ids` (special case). Only last token logits are needed for generation, and calculating them only for that token can save memory, which becomes pretty significant for long sequences or large vocabulary size. If a `torch.Tensor`, must be 1D corresponding to the indices to keep in the sequence length dimension. This is useful when using packed tensor format (single dimension for batch and sequence length). **Returns:** `[CausalLMOutputWithCrossAttentions](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`` A [CausalLMOutputWithCrossAttentions](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([BlenderbotSmallConfig](/docs/transformers/main/en/model_doc/blenderbot-small#transformers.BlenderbotSmallConfig)) and inputs.