# Mixtral

## Overview

[Mixtral-8x7B](https://huggingface.co/papers/2401.04088) was introduced in the [Mixtral of Experts blogpost](https://mistral.ai/news/mixtral-of-experts/) by Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.

The introduction of the blog post says:

*Today, the team is proud to release Mixtral 8x7B, a high-quality sparse mixture of experts models (SMoE) with open weights. Licensed under Apache 2.0. Mixtral outperforms Llama 2 70B on most benchmarks with 6x faster inference. It is the strongest open-weight model with a permissive license and the best model overall regarding cost/performance trade-offs. In particular, it matches or outperforms GPT3.5 on most standard benchmarks.*

Mixtral-8x7B is the second large language model (LLM) released by [mistral.ai](https://mistral.ai/), after [Mistral-7B](mistral).

### Architectural details

Mixtral-8x7B is a decoder-only Transformer with the following architectural choices:

- Mixtral is a Mixture of Experts (MoE) model with 8 experts per MLP, with a total of 45 billion parameters. To learn more about mixture-of-experts, refer to the [blog post](https://huggingface.co/blog/moe).
- Despite the model having 45 billion parameters, the compute required for a single forward pass is the same as that of a 14 billion parameter model. This is because even though each of the experts have to be loaded in RAM (70B like ram requirement) each token from the hidden states are dispatched twice (top 2 routing) and thus the compute (the operation required at each forward computation) is just 2 X sequence_length.

The following implementation details are shared with Mistral AI's first model [Mistral-7B](mistral):

- Sliding Window Attention - Trained with 8k context length and fixed cache size, with a theoretical attention span of 128K tokens
- GQA (Grouped Query Attention) - allowing faster inference and lower cache size.
- Byte-fallback BPE tokenizer - ensures that characters are never mapped to out of vocabulary tokens.

For more details refer to the [release blog post](https://mistral.ai/news/mixtral-of-experts/).

### License

`Mixtral-8x7B` is released under the Apache 2.0 license.

## Usage tips

The Mistral team has released 2 checkpoints:

- a base model, [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1), which has been pre-trained to predict the next token on internet-scale data.
- an instruction tuned model, [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1), which is the base model optimized for chat purposes using supervised fine-tuning (SFT) and direct preference optimization (DPO).

The base model can be used as follows:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-v0.1", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-v0.1")

prompt = "My favourite condiment is"

model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)

generated_ids = model.generate(**model_inputs, max_new_tokens=100, do_sample=True)
tokenizer.batch_decode(generated_ids)[0]
"My favourite condiment is to ..."
```

The instruction tuned model can be used as follows:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1")

messages = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)

generated_ids = model.generate(model_inputs, max_new_tokens=100, do_sample=True)
tokenizer.batch_decode(generated_ids)[0]
"Mayonnaise can be made as follows: (...)"
```

As can be seen, the instruction-tuned model requires a [chat template](../chat_templating) to be applied to make sure the inputs are prepared in the right format.

## Speeding up Mixtral by using Flash Attention

The code snippets above showcase inference without any optimization tricks. However, one can drastically speed up the model by leveraging [Flash Attention](../perf_train_gpu_one#flash-attention-2), which is a faster implementation of the attention mechanism used inside the model.

First, make sure to install the latest version of Flash Attention 2 to include the sliding window attention feature.

```bash
pip install -U flash-attn --no-build-isolation
```

Make also sure that you have a hardware that is compatible with Flash-Attention 2. Read more about it in the official documentation of the [flash attention repository](https://github.com/Dao-AILab/flash-attention). Make also sure to load your model in half-precision (e.g. `torch.float16`)

To load and run a model using Flash Attention-2, refer to the snippet below:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-v0.1", attn_implementation="flash_attention_2", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-v0.1")

prompt = "My favourite condiment is"

model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)

generated_ids = model.generate(**model_inputs, max_new_tokens=100, do_sample=True)
tokenizer.batch_decode(generated_ids)[0]
"The expected output"
```

### Expected speedups

Below is a expected speedup diagram that compares pure inference time between the native implementation in transformers using `mistralai/Mixtral-8x7B-v0.1` checkpoint and the Flash Attention 2 version of the model.

### Sliding window Attention

The current implementation supports the sliding window attention mechanism and memory efficient cache management.
To enable sliding window attention, just make sure to have a `flash-attn` version that is compatible with sliding window attention (`>=2.3.0`).

The Flash Attention-2 model uses also a more memory efficient cache slicing mechanism - as recommended per the official implementation of Mistral model that use rolling cache mechanism we keep the cache size fixed (`self.config.sliding_window`), support batched generation only for `padding_side="left"` and use the absolute position of the current token to compute the positional embedding.

## Shrinking down Mixtral using quantization

As the Mixtral model has 45 billion parameters, that would require about 90GB of GPU RAM in half precision (float16), since each parameter is stored in 2 bytes. However, one can shrink down the size of the model using [quantization](../quantization/overview). If the model is quantized to 4 bits (or half a byte per parameter), a single A100 with 40GB of RAM is enough to fit the entire model, as in that case only about 27 GB of RAM is required.

Quantizing a model is as simple as passing a `quantization_config` to the model. Below, we'll leverage the bitsandbytes quantization library (but refer to [this page](../quantization/overview) for alternative quantization methods):

```python
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig

# specify how to quantize the model
quantization_config = BitsAndBytesConfig(
        load_in_4bit=True,
        bnb_4bit_quant_type="nf4",
        bnb_4bit_compute_dtype="torch.float16",
)

model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1", quantization_config=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1")

prompt = "My favourite condiment is"

messages = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)

generated_ids = model.generate(model_inputs, max_new_tokens=100, do_sample=True)
tokenizer.batch_decode(generated_ids)[0]
"The expected output"
```

This model was contributed by [Younes Belkada](https://huggingface.co/ybelkada) and [Arthur Zucker](https://huggingface.co/ArthurZ) .
The original code can be found [here](https://github.com/mistralai/mistral-src).

## Resources

A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with Mixtral. If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.

- A demo notebook to perform supervised fine-tuning (SFT) of Mixtral-8x7B can be found [here](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/Mistral/Supervised_fine_tuning_(SFT)_of_an_LLM_using_Hugging_Face_tooling.ipynb). 🌎
- A [blog post](https://medium.com/@prakharsaxena11111/finetuning-mixtral-7bx8-6071b0ebf114) on fine-tuning Mixtral-8x7B using PEFT. 🌎
- The [Alignment Handbook](https://github.com/huggingface/alignment-handbook) by Hugging Face includes scripts and recipes to perform supervised fine-tuning (SFT) and direct preference optimization with Mistral-7B. This includes scripts for full fine-tuning, QLoRa on a single accelerator as well as multi-accelerator fine-tuning.
- [Causal language modeling task guide](../tasks/language_modeling)

## MixtralConfig[[transformers.MixtralConfig]]

- **vocab_size** (`int`, *optional*, defaults to `32000`) --
  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 `14336`) --
  Dimension of the MLP representations.
- **num_hidden_layers** (`int`, *optional*, defaults to `32`) --
  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 `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. 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](https://huggingface.co/papers/2305.13245). If it is not specified, will default to
  `num_attention_heads`.
- **head_dim** (`int`, *optional*) --
  The attention head dimension. If None, it will default to hidden_size // num_attention_heads
- **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 `131072`) --
  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-05`) --
  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*) --
  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.
- **tie_word_embeddings** (`bool`, *optional*, defaults to `False`) --
  Whether to tie weight embeddings according to model's `tied_weights_keys` mapping.
- **sliding_window** (`int`, *optional*) --
  Sliding window attention window size. If `None`, no sliding window is applied.
- **attention_dropout** (`Union[float, int]`, *optional*, defaults to `0.0`) --
  The dropout ratio for the attention probabilities.
- **num_experts_per_tok** (`int`, *optional*, defaults to `2`) --
  Number of experts to route each token to. This is the top-k value for the token-choice routing.
- **num_local_experts** (`int`, *optional*, defaults to `8`) --
  Number of local experts on each device. `num_experts` should be divisible by `num_local_experts`.
- **output_router_logits** (`bool`, *optional*, defaults to `False`) --
  Whether or not the router logits should be returned by the model. Enabling this will also allow the model
  to output the auxiliary loss, including load balancing loss and router z-loss.
- **router_aux_loss_coef** (`float`, *optional*, defaults to `0.001`) --
  Auxiliary load balancing loss coefficient. Used to penalize uneven expert routing in MoE models.
- **router_jitter_noise** (`float`, *optional*, defaults to `0.0`) --
  Amount of noise to add to the router logits during training for better load balancing.
- **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`.

This is the configuration class to store the configuration of a MixtralModel. It is used to instantiate a Mixtral
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/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1)

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 MixtralModel, MixtralConfig

>>> # Initializing a Mixtral 7B style configuration
>>> configuration = MixtralConfig()

>>> # Initializing a model from the Mixtral 7B style configuration
>>> model = MixtralModel(configuration)

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

## MistralCommonBackend[[transformers.MistralCommonBackend]]

## MixtralModel[[transformers.MixtralModel]]

- **config** ([MixtralConfig](/docs/transformers/main/en/model_doc/mixtral#transformers.MixtralConfig)) --
  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.

The bare Mixtral 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.

- **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)
- **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/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.
- **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`).`MoeModelOutputWithPast` or `tuple(torch.FloatTensor)`A `MoeModelOutputWithPast` 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 ([MixtralConfig](/docs/transformers/main/en/model_doc/mixtral#transformers.MixtralConfig)) and inputs.
The [MixtralModel](/docs/transformers/main/en/model_doc/mixtral#transformers.MixtralModel) 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.
- **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 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.
- **router_logits** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_router_probs=True` and `config.add_router_probs=True` is passed or when `config.output_router_probs=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`.

  Raw router logtis (post-softmax) that are computed by MoE routers, these terms are used to compute the auxiliary
  loss for Mixture of Experts models.

## MixtralForCausalLM[[transformers.MixtralForCausalLM]]

- **config** ([MixtralForCausalLM](/docs/transformers/main/en/model_doc/mixtral#transformers.MixtralForCausalLM)) --
  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.

The Mixtral Model for causal language modeling.

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.

- **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)
- **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/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`).
- **output_router_logits** (`bool`, *optional*) --
  Whether or not to return the logits of all the routers. They are useful for computing the router loss, and
  should not be returned during inference.
- **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).`MoeCausalLMOutputWithPast` or `tuple(torch.FloatTensor)`A `MoeCausalLMOutputWithPast` 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 ([MixtralConfig](/docs/transformers/main/en/model_doc/mixtral#transformers.MixtralConfig)) and inputs.
The [MixtralForCausalLM](/docs/transformers/main/en/model_doc/mixtral#transformers.MixtralForCausalLM) 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).
- **aux_loss** (`torch.FloatTensor`, *optional*, returned when `labels` is provided) -- aux_loss for the sparse modules.
- **router_logits** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_router_probs=True` and `config.add_router_probs=True` is passed or when `config.output_router_probs=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`.

  Raw router logtis (post-softmax) that are computed by MoE routers, these terms are used to compute the auxiliary
  loss for Mixture of Experts models.
- **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 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:

```python
>>> from transformers import AutoTokenizer, MixtralForCausalLM

>>> model = MixtralForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-v0.1")
>>> tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-v0.1")

>>> 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."
```

## MixtralForSequenceClassification[[transformers.MixtralForSequenceClassification]]

- **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)
- **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`, *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`).`SequenceClassifierOutputWithPast`
The `GenericForSequenceClassification` 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.

## MixtralForTokenClassification[[transformers.MixtralForTokenClassification]]

- **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)
- **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`, *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`).`TokenClassifierOutput`
The `GenericForTokenClassification` 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.

## MixtralForQuestionAnswering[[transformers.MixtralForQuestionAnswering]]

- **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)
- **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`, *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.
- **start_positions** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) --
  Labels for position (index) of the start of the labelled span for computing the token classification loss.
  Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
  are not taken into account for computing the loss.
- **end_positions** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) --
  Labels for position (index) of the end of the labelled span for computing the token classification loss.
  Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
  are not taken into account for computing the loss.`QuestionAnsweringModelOutput`
The `GenericForQuestionAnswering` 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.