Hugging Face's logo

Transformers documentation

Mistral4

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v5.3.0).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

This model was released on 2026-03-16 and added to Hugging Face Transformers on 2026-03-16.

Mistral4

Overview

Mistral 4 is a powerful hybrid model with the capability of acting as both a general instruction model and a reasoning model. It unifies the capabilities of three different model families - Instruct, Reasoning ( previous called Magistral ), and Devstral - into a single, unified model.

Mistral-Small-4 consists of the following architectural choices:

  • MoE: 128 experts and 4 active.
  • 119B with 6.5B activated parameters per token.
  • 256k Context Length.
  • Multimodal Input: Accepts both text and image input, with text output.
  • Instruct and Reasoning functionalities with Function Calls
    • Reasoning Effort configurable by request.

Mistral 4 offers the following capabilities:

  • Reasoning Mode: Switch between a fast instant reply mode, and a reasoning thinking mode, boosting performance with test time compute when requested.
  • Vision: Enables the model to analyze images and provide insights based on visual content, in addition to text.
  • Multilingual: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic.
  • System Prompt: Maintains strong adherence and support for system prompts.
  • Agentic: Offers best-in-class agentic capabilities with native function calling and JSON outputting.
  • Speed-Optimized: Delivers best-in-class performance and speed.
  • Apache 2.0 License: Open-source license allowing usage and modification for both commercial and non-commercial purposes.
  • Large Context Window: Supports a 256k context window.

Usage examples

import torch
from transformers import AutoProcessor, Mistral3ForConditionalGeneration


model_id = "mistralai/Mistral-Small-4-119B-2603"

processor = AutoProcessor.from_pretrained(model_id)
model = Mistral3ForConditionalGeneration.from_pretrained(
    model_id, device_map="auto"
)

image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
            },
            {"type": "image_url", "image_url": {"url": image_url}},
        ],
    },
]

inputs = processor.apply_chat_template(messages, return_tensors="pt", tokenize=True, return_dict=True, reasoning_effort="high")
inputs = inputs.to(model.device)

output = model.generate(
    **inputs,
    max_new_tokens=512,
)[0]

# Setting `skip_special_tokens=False` to visualize reasoning trace between [THINK] [/THINK] tags.
decoded_output = processor.decode(output[len(inputs["input_ids"][0]):], skip_special_tokens=False) 
print(decoded_output)

Mistral4Config

class transformers.Mistral4Config

< >

( output_hidden_states: bool | None = False return_dict: bool | None = True dtype: typing.Union[str, ForwardRef('torch.dtype'), NoneType] = None chunk_size_feed_forward: int = 0 is_encoder_decoder: bool = False id2label: dict[int, str] | dict[str, str] | None = None label2id: dict[str, int] | dict[str, str] | None = None problem_type: typing.Optional[typing.Literal['regression', 'single_label_classification', 'multi_label_classification']] = None tokenizer_class: str | None = None vocab_size: int = 131072 hidden_size: int = 4096 intermediate_size: int = 12288 moe_intermediate_size: int = 2048 num_hidden_layers: int = 36 num_attention_heads: int = 32 num_key_value_heads: int | None = 32 n_shared_experts: int = 1 n_routed_experts: int = 128 routed_scaling_factor: float = 1.0 kv_lora_rank: int = 256 q_lora_rank: int = 1024 qk_rope_head_dim: int = 64 v_head_dim: int | None = 128 qk_nope_head_dim: int = 64 n_group: int | None = 1 topk_group: int | None = 1 num_experts_per_tok: int | None = 4 first_k_dense_replace: int | None = 0 norm_topk_prob: bool | None = True hidden_act: str = 'silu' max_position_embeddings: int = 1048576 initializer_range: float = 0.02 rms_norm_eps: float = 1e-06 use_cache: bool = True pad_token_id: int | None = 11 bos_token_id: int | None = 1 eos_token_id: int | None = 2 pretraining_tp: int | None = 1 tie_word_embeddings: bool = False rope_parameters: transformers.modeling_rope_utils.RopeParameters | dict | None = None rope_interleave: bool | None = True attention_bias: bool = False attention_dropout: float | int | None = 0.0 )

Parameters

  • output_hidden_states (bool, optional, defaults to False) — Whether or not the model should return all hidden-states.
  • return_dict (bool, optional, defaults to True) — Whether to return a ModelOutput (dataclass) instead of a plain tuple.
  • dtype (Union[str, torch.dtype], optional) — The chunk size of all feed forward layers in the residual attention blocks. A chunk size of 0 means that the feed forward layer is not chunked. A chunk size of n means that the feed forward layer processes n < sequence_length embeddings at a time. For more information on feed forward chunking, see How does Feed Forward Chunking work?.
  • chunk_size_feed_forward (int, optional, defaults to 0) — The dtype of the weights. This attribute can be used to initialize the model to a non-default dtype (which is normally float32) and thus allow for optimal storage allocation. For example, if the saved model is float16, ideally we want to load it back using the minimal amount of memory needed to load float16 weights.
  • is_encoder_decoder (bool, optional, defaults to False) — Whether the model is used as an encoder/decoder or not.
  • id2label (Union[dict[int, str], dict[str, str]], optional) — A map from index (for instance prediction index, or target index) to label.
  • label2id (Union[dict[str, int], dict[str, str]], optional) — A map from label to index for the model.
  • problem_type (Literal[regression, single_label_classification, multi_label_classification], optional) — Problem type for XxxForSequenceClassification models. Can be one of "regression", "single_label_classification" or "multi_label_classification".
  • tokenizer_class (str, optional) — The class name of model’s tokenizer.
  • vocab_size (int, optional, defaults to 131072) — 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 12288) — Dimension of the MLP representations.
  • moe_intermediate_size (int, optional, defaults to 2048) — Intermediate size of the routed expert MLPs.
  • num_hidden_layers (int, optional, defaults to 36) — Number of hidden layers in the Transformer decoder.
  • num_attention_heads (int, optional, defaults to 32) — Number of attention heads for each attention layer in the Transformer decoder.
  • num_key_value_heads (int, optional, defaults to 32) — This is the number of key_value heads that should be used to implement Grouped Query Attention. If num_key_value_heads=num_attention_heads, the model will use Multi Head Attention (MHA), if num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details, check out this paper. If it is not specified, will default to num_attention_heads.
  • n_shared_experts (int, optional, defaults to 1) — Number of shared experts.
  • n_routed_experts (int, optional, defaults to 128) — Number of routed experts.
  • routed_scaling_factor (float, optional, defaults to 1.0) — Scaling factor or routed experts.
  • kv_lora_rank (int, optional, defaults to 256) — Rank of the LoRA matrices for key and value projections.
  • q_lora_rank (int, optional, defaults to 1024) — Rank of the LoRA matrices for query projections.
  • qk_rope_head_dim (int, optional, defaults to 64) — Dimension of the query/key heads that use rotary position embeddings.
  • v_head_dim (int, optional, defaults to 128) — Dimension of the value heads.
  • qk_nope_head_dim (int, optional, defaults to 64) — Dimension of the query/key heads that don’t use rotary position embeddings.
  • n_group (int, optional, defaults to 1) — Number of groups for routed experts.
  • topk_group (int, optional, defaults to 1) — Number of selected groups for each token (for each token, ensuring the selected experts is only within topk_group groups).
  • num_experts_per_tok (int, optional, defaults to 4) — Number of experts to route each token to. This is the top-k value for the token-choice routing.
  • first_k_dense_replace (int, optional, defaults to 0) — Number of dense layers in shallow layers(embed->dense->dense->…->dense->moe->moe…->lm_head). --k dense layers—/
  • norm_topk_prob (bool, optional, defaults to True) — Whether to normalize the weights of the routed experts.
  • hidden_act (str, optional, defaults to silu) — The non-linear activation function (function or string) in the decoder. For example, "gelu", "relu", "silu", etc.
  • max_position_embeddings (int, optional, defaults to 1048576) — The maximum sequence length that this model might ever be used with.
  • initializer_range (float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
  • rms_norm_eps (float, optional, defaults to 1e-06) — The epsilon used by the rms normalization layers.
  • use_cache (bool, optional, defaults to True) — Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if config.is_decoder=True or when the model is a decoder-only generative model.
  • pad_token_id (int, optional, defaults to 11) — 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 (int, optional, defaults to 2) — Token id used for end-of-stream in the vocabulary.
  • pretraining_tp (int, optional, defaults to 1) — Experimental feature. Tensor parallelism rank used during pretraining. Please refer to this document to understand more about it. This value is necessary to ensure exact reproducibility of the pretraining results. Please refer to this issue.
  • 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.
  • rope_interleave (bool, optional, defaults to True) — Whether to interleave the rotary position embeddings.
  • attention_bias (bool, optional, defaults to False) — Whether to use a bias in the query, key, value and output projection layers during self-attention.
  • attention_dropout (Union[float, int], optional, defaults to 0.0) — The dropout ratio for the attention probabilities.

This is the configuration class to store the configuration of a Mistral4Model. It is used to instantiate a Mistral4 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 mistralai/Mistral-Small-4-119B-2603

Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information.

Example:

>>> from transformers import Mistral4Model, Mistral4Config

>>> # Initializing a Mistral4 style configuration
>>> configuration = Mistral4Config()

>>> # Accessing the model configuration
>>> configuration = model.config

Mistral4PreTrainedModel

class transformers.Mistral4PreTrainedModel

< >

( config: PreTrainedConfig *inputs **kwargs )

_forward_unimplemented

< >

( *input: typing.Any )

Define the computation performed at every call.

Should be overridden by all subclasses.

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 registered hooks while the latter silently ignores them.

Mistral4Model

class transformers.Mistral4Model

< >

( config: Mistral4Config )

Parameters

  • config (Mistral4Config) — 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() method to load the model weights.

The bare Mistral4 Model outputting raw hidden-states without any specific head on top.

This model inherits from 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 subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( input_ids: torch.LongTensor | None = None attention_mask: torch.Tensor | None = None position_ids: torch.LongTensor | None = None past_key_values: transformers.cache_utils.Cache | None = None inputs_embeds: torch.FloatTensor | None = None use_cache: bool | None = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → BaseModelOutputWithPast or tuple(torch.FloatTensor)

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. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are 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?

  • 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?

  • 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 instance is allowed as input, see our kv cache guide. If no past_key_values are passed, 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).

Returns

BaseModelOutputWithPast or tuple(torch.FloatTensor)

A BaseModelOutputWithPast 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 (Mistral4Config) and inputs.

The Mistral4Model 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 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 (Cache, optional, returned when use_cache=True is passed or when config.use_cache=True) — It is a Cache instance. For more details, see our kv cache guide.

    Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if config.is_encoder_decoder=True in the cross-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.

Mistral4ForCausalLM

class transformers.Mistral4ForCausalLM

< >

( config )

Parameters

  • config (Mistral4ForCausalLM) — 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() method to load the model weights.

The Mistral4 Model for causal language modeling.

This model inherits from 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 subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( input_ids: torch.LongTensor | None = None attention_mask: torch.Tensor | None = None position_ids: torch.LongTensor | None = None past_key_values: transformers.cache_utils.Cache | None = None inputs_embeds: torch.FloatTensor | None = None labels: torch.LongTensor | None = None use_cache: bool | None = None logits_to_keep: int | torch.Tensor = 0 **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → CausalLMOutputWithPast or tuple(torch.FloatTensor)

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. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are 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?

  • 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?

  • 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 instance is allowed as input, see our kv cache guide. If no past_key_values are passed, 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

CausalLMOutputWithPast or tuple(torch.FloatTensor)

A 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 (Mistral4Config) and inputs.

The Mistral4ForCausalLM 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 instance. For more details, see our kv cache guide.

    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.

Example:

>>> from transformers import AutoTokenizer, Mistral4ForCausalLM

>>> model = Mistral4ForCausalLM.from_pretrained("meta-mistral4/Mistral4-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-mistral4/Mistral4-2-7b-hf")

>>> prompt = "Hey, are you conscious? Can you talk to me?"
>>> inputs = tokenizer(prompt, return_tensors="pt")

>>> # Generate
>>> generate_ids = model.generate(inputs.input_ids, max_length=30)
>>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."

Mistral4ForSequenceClassification

class transformers.Mistral4ForSequenceClassification

< >

( config )

Mistral4ForTokenClassification

class transformers.Mistral4ForTokenClassification

< >

( config )

Update on GitHub

←Mistral3 mllama→