# Fuyu ## Overview The Fuyu model was created by [ADEPT](https://www.adept.ai/blog/fuyu-8b), and authored by Rohan Bavishi, Erich Elsen, Curtis Hawthorne, Maxwell Nye, Augustus Odena, Arushi Somani, Sağnak Taşırlar. The authors introduced Fuyu-8B, a decoder-only multimodal model based on the classic transformers architecture, with query and key normalization. A linear encoder is added to create multimodal embeddings from image inputs. By treating image tokens like text tokens and using a special image-newline character, the model knows when an image line ends. Image positional embeddings are removed. This avoids the need for different training phases for various image resolutions. With 8 billion parameters and licensed under CC-BY-NC, Fuyu-8B is notable for its ability to handle both text and images, its impressive context size of 16K, and its overall performance. The `Fuyu` models were trained using `bfloat16`, but the original inference uses `float16` The checkpoints uploaded on the hub use `dtype = 'float16'` which will be used by the `AutoModel` API to cast the checkpoints from `torch.float32` to `torch.float16`. The `dtype` of the online weights is mostly irrelevant, unless you are using `dtype="auto"` when initializing a model using `model = AutoModelForCausalLM.from_pretrained("path", dtype = "auto")`. The reason is that the model will first be downloaded ( using the `dtype` of the checkpoints online) then it will be cast to the default `dtype` of `torch` (becomes `torch.float32`, device_map="auto"). Users should specify the `dtype` they want, and if they don't it will be `torch.float32`. Finetuning the model in `float16` is not recommended and known to produce `nan`, as such the model should be fine-tuned in `bfloat16`. Tips: - To convert the model, you need to clone the original repository using `git clone https://github.com/persimmon-ai-labs/adept-inference`, then get the checkpoints: ```bash git clone https://github.com/persimmon-ai-labs/adept-inference wget path/to/fuyu-8b-model-weights.tar tar -xvf fuyu-8b-model-weights.tar python src/transformers/models/fuyu/convert_fuyu_weights_to_hf.py --input_dir /path/to/downloaded/fuyu/weights/ --output_dir /output/path \ --pt_model_path /path/to/fuyu_8b_release/iter_0001251/mp_rank_00/model_optim_rng.pt --ada_lib_path /path/to/adept-inference ``` For the chat model: ```bash wget https://axtkn4xl5cip.objectstorage.us-phoenix-1.oci.customer-oci.com/n/axtkn4xl5cip/b/adept-public-data/o/8b_chat_model_release.tar tar -xvf 8b_base_model_release.tar ``` Then, model can be loaded via: ```python from transformers import FuyuConfig, FuyuForCausalLM model_config = FuyuConfig() model = FuyuForCausalLM(model_config).from_pretrained('/output/path') ``` Inputs need to be passed through a specific Processor to have the correct formats. A processor requires an image_processor and a tokenizer. Hence, inputs can be loaded via: ```python from PIL import Image from transformers import AutoTokenizer from transformers.models.fuyu.image_processing_fuyu import FuyuImageProcessor from transformers.models.fuyu.processing_fuyu import FuyuProcessor tokenizer = AutoTokenizer.from_pretrained('adept-hf-collab/fuyu-8b') image_processor = FuyuImageProcessor() processor = FuyuProcessor(image_processor=image_processor, tokenizer=tokenizer) text_prompt = "Generate a coco-style caption.\\n" bus_image_url = "https://huggingface.co/datasets/hf-internal-testing/fixtures-captioning/resolve/main/bus.png" bus_image_pil = Image.open(io.BytesIO(requests.get(bus_image_url).content)) inputs_to_model = processor(images=bus_image_pil, text=text_prompt) ``` This model was contributed by [Molbap](https://huggingface.co/Molbap). The original code can be found [here](https://github.com/persimmon-ai-labs/adept-inference). - Fuyu uses a `sentencepiece` based tokenizer, with a `Unigram` model. It supports bytefallback, which is only available in `tokenizers==0.14.0` for the fast tokenizer. The `LlamaTokenizer` is used as it is a standard wrapper around sentencepiece. - The authors suggest to use the following prompt for image captioning: `f"Generate a coco-style caption.\\n"` ## FuyuConfig[[transformers.FuyuConfig]] #### transformers.FuyuConfig[[transformers.FuyuConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fuyu/configuration_fuyu.py#L29) This is the configuration class to store the configuration of a FuyuModel. It is used to instantiate a Fuyu 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 [adept/fuyu-8b](https://huggingface.co/adept/fuyu-8b) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import FuyuConfig >>> # Initializing a Fuyu fuyu-7b style configuration >>> configuration = FuyuConfig() ``` **Parameters:** vocab_size (`int`, *optional*, defaults to `262144`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`. hidden_size (`int`, *optional*, defaults to `4096`) : Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to `16384`) : Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to `36`) : Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to `64`) : Number of attention heads for each attention layer in the Transformer decoder. hidden_act (`str`, *optional*, defaults to `relu2`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc. max_position_embeddings (`int`, *optional*, defaults to `16384`) : The maximum sequence length that this model might ever be used with. image_size (`int`, *optional*, defaults to `300`) : The size (resolution) of each image. patch_size (`int`, *optional*, defaults to `30`) : The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to `3`) : The number of input channels. initializer_range (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to `1e-05`) : The epsilon used by the layer 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` or when the model is a decoder-only generative model. tie_word_embeddings (`bool`, *optional*, defaults to `False`) : Whether to tie weight embeddings according to model's `tied_weights_keys` mapping. rope_parameters (`Union[~modeling_rope_utils.RopeParameters, dict]`, *optional*) : Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE with longer `max_position_embeddings`. qk_layernorm (`bool`, *optional*, defaults to `True`) : Whether to use query-key normalization in the attention. hidden_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities. pad_token_id (`int`, *optional*) : 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. image_token_id (`int`, *optional*, defaults to `71011`) : The image token index used as a placeholder for input images. text_config (`Union[dict, ~configuration_utils.PreTrainedConfig]`, *optional*) : The config object or dictionary of the text backbone. ## FuyuModel[[transformers.FuyuModel]] #### transformers.FuyuModel[[transformers.FuyuModel]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fuyu/modeling_fuyu.py#L51) The Fuyu model which consists of a vision backbone and a language model, without a language modeling head. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.FuyuModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fuyu/modeling_fuyu.py#L151[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "image_patches", "val": ": torch.Tensor | None = None"}, {"name": "image_patches_indices", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "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/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **image_patches** (`torch.FloatTensor` of shape `(batch_size, num_total_patches, patch_size_ x patch_size x num_channels)`, *optional*) -- Image patches to be used as continuous embeddings. The patches are flattened and then projected to the hidden size of the model. - **image_patches_indices** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Tensor of indices of the image patches in the input_ids tensor. - **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) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **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/v5.8.0/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/v5.8.0/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. - **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[CausalLMOutputWithPast](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) or `tuple(torch.FloatTensor)`A [CausalLMOutputWithPast](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) 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 ([FuyuConfig](/docs/transformers/v5.8.0/en/model_doc/fuyu#transformers.FuyuConfig)) and inputs. The [FuyuModel](/docs/transformers/v5.8.0/en/model_doc/fuyu#transformers.FuyuModel) 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). - **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.8.0/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 self-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. - **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. **Parameters:** config ([FuyuConfig](/docs/transformers/v5.8.0/en/model_doc/fuyu#transformers.FuyuConfig)) : 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/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[CausalLMOutputWithPast](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) or `tuple(torch.FloatTensor)`` A [CausalLMOutputWithPast](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) 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 ([FuyuConfig](/docs/transformers/v5.8.0/en/model_doc/fuyu#transformers.FuyuConfig)) and inputs. #### gather_continuous_embeddings[[transformers.FuyuModel.gather_continuous_embeddings]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fuyu/modeling_fuyu.py#L71) This function places the continuous_embeddings into the word_embeddings at the locations indicated by image_patch_input_indices. Different batch elements can have different numbers of continuous embeddings. **Parameters:** word_embeddings (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) : Tensor of word embeddings. continuous_embeddings (`torch.FloatTensor` of shape `(batch_size, num_patches, hidden_size)`) : Tensor of continuous embeddings. The length of the list is the batch size. Each entry is shape [num_image_embeddings, hidden], and num_image_embeddings needs to match the number of non-negative indices in image_patch_input_indices for that batch element. image_patch_input_indices (`torch.LongTensor` of shape `(batch_size, sequence_length)`) : Tensor of indices of the image patches in the input_ids tensor. #### get_image_features[[transformers.FuyuModel.get_image_features]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fuyu/modeling_fuyu.py#L115) - **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 model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **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. **Parameters:** pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`) : The tensors corresponding to the input images. **Returns:** `[BaseModelOutputWithPooling](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPooling](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) 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 ([FuyuConfig](/docs/transformers/v5.8.0/en/model_doc/fuyu#transformers.FuyuConfig)) and inputs. #### get_placeholder_mask[[transformers.FuyuModel.get_placeholder_mask]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fuyu/modeling_fuyu.py#L127) Obtains multimodal placeholder mask from `input_ids` or `inputs_embeds`, and checks that the placeholder token count is equal to the length of multimodal features. If the lengths are different, an error is raised. ## FuyuForCausalLM[[transformers.FuyuForCausalLM]] #### transformers.FuyuForCausalLM[[transformers.FuyuForCausalLM]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fuyu/modeling_fuyu.py#L214) Fuyu Model with a language modeling head on top for causal language model conditioned on image patches and text. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.FuyuForCausalLM.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fuyu/modeling_fuyu.py#L229[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "image_patches", "val": ": torch.Tensor | None = None"}, {"name": "image_patches_indices", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "labels", "val": ": torch.Tensor | None = None"}, {"name": "logits_to_keep", "val": ": int | None = 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/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **image_patches** (`torch.FloatTensor` of shape `(batch_size, num_total_patches, patch_size_ x patch_size x num_channels)`, *optional*) -- Image patches to be used as continuous embeddings. The patches are flattened and then projected to the hidden size of the model. - **image_patches_indices** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Tensor of indices of the image patches in the input_ids tensor. - **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) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **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/v5.8.0/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/v5.8.0/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. - **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`). - **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.text_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.text_config.vocab_size]`. - **logits_to_keep** (`int`, *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[CausalLMOutputWithPast](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) or `tuple(torch.FloatTensor)`A [CausalLMOutputWithPast](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) 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 ([FuyuConfig](/docs/transformers/v5.8.0/en/model_doc/fuyu#transformers.FuyuConfig)) and inputs. The [FuyuForCausalLM](/docs/transformers/v5.8.0/en/model_doc/fuyu#transformers.FuyuForCausalLM) 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). - **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.8.0/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 self-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. - **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. Examples: ```python >>> from transformers import FuyuProcessor, FuyuForCausalLM >>> from PIL import Image >>> import httpx >>> from io import BytesIO >>> processor = FuyuProcessor.from_pretrained("adept/fuyu-8b") >>> model = FuyuForCausalLM.from_pretrained("adept/fuyu-8b") >>> url = "https://huggingface.co/datasets/hf-internal-testing/fixtures-captioning/resolve/main/bus.png" >>> with httpx.stream("GET", url) as response: ... image = Image.open(BytesIO(response.read())) >>> prompt = "Generate a coco-style caption.\n" >>> inputs = processor(images=image, text=prompt, return_tensors="pt") >>> outputs = model(**inputs) >>> generated_ids = model.generate(**inputs, max_new_tokens=7) >>> generation_text = processor.batch_decode(generated_ids[:, -7:], skip_special_tokens=True) >>> print(generation_text[0]) A blue bus parked on the side of a road. ``` **Parameters:** config ([FuyuConfig](/docs/transformers/v5.8.0/en/model_doc/fuyu#transformers.FuyuConfig)) : 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/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[CausalLMOutputWithPast](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) or `tuple(torch.FloatTensor)`` A [CausalLMOutputWithPast](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) 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 ([FuyuConfig](/docs/transformers/v5.8.0/en/model_doc/fuyu#transformers.FuyuConfig)) and inputs. ## FuyuImageProcessor[[transformers.FuyuImageProcessor]] #### transformers.FuyuImageProcessor[[transformers.FuyuImageProcessor]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fuyu/image_processing_fuyu.py#L185) Constructs a FuyuImageProcessor image processor. preprocesstransformers.FuyuImageProcessor.preprocesshttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/image_processing_utils.py#L382[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]"}, {"name": "*args", "val": ""}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.processing_utils.ImagesKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **return_tensors** (`str` or [TensorType](/docs/transformers/v5.8.0/en/internal/file_utils#transformers.TensorType), *optional*) -- Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors. - ****kwargs** ([ImagesKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ImagesKwargs), *optional*) -- Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.0`~image_processing_base.BatchFeature`- **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. **Parameters:** patch_size (`dict[str, *kwargs*, int]`, *optional*, defaults to `{"height" : 30, "width": 30}`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the patches. padding_value (`float`, *kwargs*, *optional*, defaults to 1.0) : The value to pad the image with. padding_mode (`str`, *kwargs*, *optional*, defaults to "constant") : The padding mode to use when padding the image. - ****kwargs** ([ImagesKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ImagesKwargs), *optional*) : Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments. **Returns:** ``~image_processing_base.BatchFeature`` - **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. ## FuyuImageProcessorPil[[transformers.FuyuImageProcessorPil]] #### transformers.FuyuImageProcessorPil[[transformers.FuyuImageProcessorPil]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fuyu/image_processing_pil_fuyu.py#L189) Constructs a FuyuImageProcessor image processor. preprocesstransformers.FuyuImageProcessorPil.preprocesshttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/image_processing_utils.py#L382[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]"}, {"name": "*args", "val": ""}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.processing_utils.ImagesKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **return_tensors** (`str` or [TensorType](/docs/transformers/v5.8.0/en/internal/file_utils#transformers.TensorType), *optional*) -- Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors. - ****kwargs** ([ImagesKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ImagesKwargs), *optional*) -- Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.0`~image_processing_base.BatchFeature`- **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. **Parameters:** patch_size (`dict[str, *kwargs*, int]`, *optional*, defaults to `{"height" : 30, "width": 30}`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the patches. padding_value (`float`, *kwargs*, *optional*, defaults to 1.0) : The value to pad the image with. padding_mode (`str`, *kwargs*, *optional*, defaults to "constant") : The padding mode to use when padding the image. - ****kwargs** ([ImagesKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ImagesKwargs), *optional*) : Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments. **Returns:** ``~image_processing_base.BatchFeature`` - **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. ## FuyuProcessor[[transformers.FuyuProcessor]] #### transformers.FuyuProcessor[[transformers.FuyuProcessor]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fuyu/processing_fuyu.py#L336) Constructs a FuyuProcessor which wraps a image processor and a tokenizer into a single processor. [FuyuProcessor](/docs/transformers/v5.8.0/en/model_doc/fuyu#transformers.FuyuProcessor) offers all the functionalities of [FuyuImageProcessor](/docs/transformers/v5.8.0/en/model_doc/fuyu#transformers.FuyuImageProcessor) and [TokenizersBackend](/docs/transformers/v5.8.0/en/main_classes/tokenizer#transformers.TokenizersBackend). See the [~FuyuImageProcessor](/docs/transformers/v5.8.0/en/model_doc/fuyu#transformers.FuyuImageProcessor) and [~TokenizersBackend](/docs/transformers/v5.8.0/en/main_classes/tokenizer#transformers.TokenizersBackend) for more information. __call__transformers.FuyuProcessor.__call__https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/fuyu/processing_fuyu.py#L485[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], NoneType] = None"}, {"name": "text", "val": ": str | list[str] | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.models.fuyu.processing_fuyu.FuyuProcessorKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`, *optional*) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **text** (`Union[str, list[str]]`, *optional*) -- The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If you pass a pretokenized input, set `is_split_into_words=True` to avoid ambiguity with batched inputs. - **return_tensors** (`str` or [TensorType](/docs/transformers/v5.8.0/en/internal/file_utils#transformers.TensorType), *optional*) -- If set, will return tensors of a particular framework. Acceptable values are: - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. - ****kwargs** ([ProcessingKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ProcessingKwargs), *optional*) -- Additional processing options for each modality (text, images, videos, audio). Model-specific parameters are listed above; see the TypedDict class for the complete list of supported arguments.0`FuyuBatchEncoding`A `FuyuBatchEncoding` with the following fields: - **input_ids** -- Tensor of token ids to be fed to a model. Returned when `text` is not `None`. - **image_patches** -- List of Tensor of image patches. Returned when `images` is not `None`. - **image_patches_indices** -- Tensor of indices where patch embeddings have to be inserted by the model. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model when `return_attention_mask=True`. **Parameters:** image_processor (`FuyuImageProcessor`) : The image processor is a required input. tokenizer (`TokenizersBackend`) : The tokenizer is a required input. **Returns:** ``FuyuBatchEncoding`` A `FuyuBatchEncoding` with the following fields: - **input_ids** -- Tensor of token ids to be fed to a model. Returned when `text` is not `None`. - **image_patches** -- List of Tensor of image patches. Returned when `images` is not `None`. - **image_patches_indices** -- Tensor of indices where patch embeddings have to be inserted by the model. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model when `return_attention_mask=True`.