Hugging Face's logo

Transformers documentation

Ministral3

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Ministral3

Overview

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

This model is the instruct post-trained version, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases.

The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.

Key features:

  • 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.
  • Edge-Optimized: Delivers best-in-class performance at a small scale, deployable anywhere.
  • 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 Mistral3ForConditionalGeneration, MistralCommonBackend


model_id = "mistralai/Ministral-3-3B-Instruct-2512"

tokenizer = MistralCommonBackend.from_pretrained(model_id)
model = Mistral3ForConditionalGeneration.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, 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}},
        ],
    },
]

tokenized = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True)

tokenized["input_ids"] = tokenized["input_ids"].to(device="cuda")
tokenized["pixel_values"] = tokenized["pixel_values"].to(dtype=torch.bfloat16, device="cuda")
image_sizes = [tokenized["pixel_values"].shape[-2:]]

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

decoded_output = tokenizer.decode(output[len(tokenized["input_ids"][0]):])
print(decoded_output)

Ministral3Config

class transformers.Ministral3Config

< >

( vocab_size: typing.Optional[int] = 131072 hidden_size: typing.Optional[int] = 4096 intermediate_size: typing.Optional[int] = 14336 num_hidden_layers: typing.Optional[int] = 34 num_attention_heads: typing.Optional[int] = 32 num_key_value_heads: typing.Optional[int] = 8 head_dim: typing.Optional[int] = 128 hidden_act: typing.Optional[str] = 'silu' max_position_embeddings: typing.Optional[int] = 262144 initializer_range: typing.Optional[float] = 0.02 rms_norm_eps: typing.Optional[float] = 1e-05 use_cache: typing.Optional[bool] = True pad_token_id: typing.Optional[int] = 11 bos_token_id: typing.Optional[int] = 1 eos_token_id: typing.Optional[int] = 2 tie_word_embeddings: typing.Optional[bool] = False rope_parameters: typing.Union[transformers.modeling_rope_utils.RopeParameters, dict[str, transformers.modeling_rope_utils.RopeParameters], NoneType] = None sliding_window: typing.Optional[int] = None attention_dropout: typing.Optional[float] = 0.0 **kwargs )

Parameters

  • vocab_size (Optional, optional, defaults to 131072) — Vocabulary size of the Ministral3 model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling Ministral3Model.
  • hidden_size (Optional, optional, defaults to 4096) — Dimensionality of the embeddings and hidden states.
  • intermediate_size (Optional, optional, defaults to 14336) — Dimensionality of the intermediate (feed-forward) layer.
  • num_hidden_layers (Optional, optional, defaults to 34) — Number of hidden layers in the Transformer decoder.
  • num_attention_heads (Optional, optional, defaults to 32) — Number of attention heads for each attention layer in the Transformer decoder.
  • num_key_value_heads (Optional, optional, defaults to 8) — 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.
  • head_dim (Optional, optional, defaults to 128) — The attention head dimension. If not specified, will default to hidden_size // num_attention_heads.
  • hidden_act (Optional, optional, defaults to "silu") — The non-linear activation function (function or string) in the decoder.
  • max_position_embeddings (Optional, optional, defaults to 262144) — The maximum sequence length that this model might ever be used with.
  • initializer_range (Optional, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
  • rms_norm_eps (Optional, optional, defaults to 1e-05) — The epsilon used by the rms normalization layers.
  • use_cache (Optional, optional, defaults to True) — Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if config.is_decoder=True.
  • pad_token_id (Optional, optional, defaults to 11) — The id of the padding token.
  • bos_token_id (Optional, optional, defaults to 1) — The id of the “beginning-of-sequence” token.
  • eos_token_id (Optional, optional, defaults to 2) — The id of the “end-of-sequence” token.
  • tie_word_embeddings (Optional, optional, defaults to False) — Whether the model’s input and output word embeddings should be tied.
  • rope_parameters (Union, optional, defaults to {'type' -- 'yarn', 'rope_theta': 1000000.0, 'factor': 16.0, 'original_max_position_embeddings': 16384, 'beta_fast': 32.0, 'beta_slow': 1.0, 'mscale_all_dim': 1.0, 'mscale': 1.0, 'llama_4_scaling_beta': 0.1}): Dictionary containing the configuration parameters for the RoPE embeddings, including optional Yarn scaling settings such as factor, original_max_position_embeddings, mscale, and llama_4_scaling_beta.
  • sliding_window (Optional, optional) — Sliding window attention window size. If None, full attention is used.
  • attention_dropout (Optional, optional, defaults to 0.0) — The dropout ratio for the attention probabilities.

This is the configuration class to store the configuration of a Ministral3Model. It is used to instantiate an Mistral 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/Ministral-3-8B-Base-2512, mistralai/Ministral-3-8B-Instruct-2512 or mistralai/Ministral-3-8B-Reasoning-2512.

mistralai/Ministral-3-8B-Base-2512 mistralai/Ministral-3-8B-Instruct-2512 mistralai/Ministral-3-8B-Reasoning-2512

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 Ministral3Config, Ministral3ForCausalLM, Mistral3Config, Mistral3ForConditionalGeneration, PixtralVisionConfig

>>> # Initializing a Pixtral-vision config
>>> vision_config = PixtralVisionConfig()

>>> # Initializing a Ministral3 config
>>> text_config = Ministral3Config()

>>> # Initializing a Mistral3 configuration
>>> configuration = Mistral3Config(vision_config, text_config)

>>> # Initializing a model from the Ministral3 configuration
>>> text_model = Ministral3ForCausalLM(text_config)

>>> # Initializing a model from the Mistral3 configuration
>>> model = Mistral3ForConditionalGeneration(configuration)

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

Ministral3PreTrainedModel

class transformers.Ministral3PreTrainedModel

< >

( config: PreTrainedConfig *inputs **kwargs )

Parameters

  • config (PreTrainedConfig) — 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.

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_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.

Ministral3Model

class transformers.Ministral3Model

< >

( config: Ministral3Config )

Parameters

  • config (Ministral3Config) — 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 Ministral3 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: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[transformers.cache_utils.Cache] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None use_cache: typing.Optional[bool] = None cache_position: typing.Optional[torch.LongTensor] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.modeling_outputs.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).
  • cache_position (torch.LongTensor of shape (sequence_length), optional) — Indices depicting the position of the input sequence tokens in the sequence. Contrarily to position_ids, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length.

Returns

transformers.modeling_outputs.BaseModelOutputWithPast or tuple(torch.FloatTensor)

A transformers.modeling_outputs.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 (Ministral3Config) and inputs.

  • 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.

The Ministral3Model 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.

Ministral3ForCausalLM

class transformers.Ministral3ForCausalLM

< >

( config )

Parameters

  • config (Ministral3ForCausalLM) — 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 Ministral3 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: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[transformers.cache_utils.Cache] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = None cache_position: typing.Optional[torch.LongTensor] = None logits_to_keep: typing.Union[int, torch.Tensor] = 0 **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.modeling_outputs.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).
  • cache_position (torch.LongTensor of shape (sequence_length), optional) — Indices depicting the position of the input sequence tokens in the sequence. Contrarily to position_ids, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length.
  • logits_to_keep (Union[int, torch.Tensor], 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

transformers.modeling_outputs.CausalLMOutputWithPast or tuple(torch.FloatTensor)

A 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 (Ministral3Config) and inputs.

  • 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.

The Ministral3ForCausalLM 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.

Example:

>>> from transformers import AutoTokenizer, Ministral3ForCausalLM

>>> model = Ministral3ForCausalLM.from_pretrained("meta-ministral3/Ministral3-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-ministral3/Ministral3-2-7b-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."

Ministral3ForSequenceClassification

class transformers.Ministral3ForSequenceClassification

< >

( config )

Ministral3ForTokenClassification

class transformers.Ministral3ForTokenClassification

< >

( config )

Ministral3ForQuestionAnswering

class transformers.Ministral3ForQuestionAnswering

< >

( config )

Update on GitHub

←Ministral Mistral→