DeepSeek-V2

Overview

The DeepSeek-V2 model was proposed in DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model by DeepSeek-AI Team.

The abstract from the paper is the following: We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which 21B are activated for each token, and supports a context length of 128K tokens. DeepSeek-V2 adopts innovative architectures including Multi-head Latent Attention (MLA) and DeepSeekMoE. MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation. Compared with DeepSeek 67B, DeepSeek-V2 achieves significantly stronger performance, and meanwhile saves 42.5% of training costs, reduces the KV cache by 93.3%, and boosts the maximum generation throughput to 5.76 times. We pretrain DeepSeek-V2 on a high-quality and multi-source corpus consisting of 8.1T tokens, and further perform Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) to fully unlock its potential. Evaluation results show that, even with only 21B activated parameters, DeepSeek-V2 and its chat versions still achieve top-tier performance among open-source models.

This model was contributed by VladOS95-cyber. The original code can be found here.

Usage tips

The model uses Multi-head Latent Attention (MLA) and DeepSeekMoE architectures for efficient inference and cost-effective training. It employs an auxiliary-loss-free strategy for load balancing and multi-token prediction training objective. The model can be used for various language tasks after being pre-trained on 14.8 trillion tokens and going through Supervised Fine-Tuning and Reinforcement Learning stages.

DeepseekV2Config

class transformers.DeepseekV2Config

< source >

( vocab_size = 32000 hidden_size = 4096 intermediate_size = 11008 num_hidden_layers = 32 num_attention_heads = 32 num_key_value_heads = None hidden_act = 'silu' max_position_embeddings = 2048 initializer_range = 0.02 rms_norm_eps = 1e-06 use_cache = True pad_token_id = None bos_token_id = 1 eos_token_id = 2 tie_word_embeddings = False rope_theta = 10000.0 rope_scaling = None attention_bias = False attention_dropout = 0.0 mlp_bias = False aux_loss_alpha = 0.001 first_k_dense_replace = 0 kv_lora_rank = 512 q_lora_rank = 1536 n_group = None n_routed_experts = 64 n_shared_experts = 2 qk_nope_head_dim = 128 qk_rope_head_dim = 64 routed_scaling_factor = 1.0 seq_aux = True topk_group = None topk_method = 'greedy' v_head_dim = 128 num_experts_per_tok = None norm_topk_prob = False moe_intermediate_size = 1407 **kwargs )

Parameters

vocab_size (int, optional, defaults to 32000) — Vocabulary size of the DeepSeek model. Defines the number of different tokens that can be represented by the input_ids passed when calling DeepseekV2Model.
hidden_size (int, optional, defaults to 4096) — Dimension of the hidden representations.
intermediate_size (int, optional, defaults to 11008) — 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) — The number of key-value heads used to implement Grouped Query Attention (GQA). 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.
hidden_act (str or function, optional, defaults to "silu") — The non-linear activation function (function or string) in the decoder.
max_position_embeddings (int, optional, defaults to 2048) — 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 value used by the RMS normalization layers.
use_cache (bool, optional, defaults to True) — Whether or not the model should return the last key/value attentions (useful for inference optimization).
pad_token_id (int, optional) — Padding token ID.
bos_token_id (int, optional, defaults to 1) — Beginning-of-sequence token ID.
eos_token_id (int, optional, defaults to 2) — End-of-sequence token ID.
tie_word_embeddings (bool, optional, defaults to False) — Whether to tie input and output embeddings.
rope_theta (float, optional, defaults to 10000.0) — The base period of the Rotary Position Embeddings (RoPE).
rope_scaling (Dict, optional) — Configuration for scaling RoPE embeddings. Supports linear and dynamic scaling strategies.
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 (float, optional, defaults to 0.0) — The dropout probability applied to attention weights.
mlp_bias (bool, optional, defaults to False) — Whether to use a bias term in the MLP layers.
aux_loss_alpha (float, optional, defaults to 0.001) — Weight coefficient for auxiliary loss in Mixture of Experts (MoE) models.
first_k_dense_replace (int, optional, defaults to 0) — Number of dense layers in the shallow layers before switching to MoE layers.
kv_lora_rank (int, optional, defaults to 512) — Rank of the LoRA decomposition for key-value projections.
q_lora_rank (int, optional, defaults to 1536) — Rank of the LoRA decomposition for query projections. Specifically, it determines the dimensionality to which the query (q) vectors are compressed before being expanded back to their original size. It reduces computational overhead while maintaining model performance.
n_group (int, optional) — Number of groups for routed experts.
n_routed_experts (int, optional, defaults to 64) — Number of routed experts (None indicates a dense model).
n_shared_experts (int, optional, defaults to 2) — Number of shared experts (None indicates a dense model).
qk_nope_head_dim (int, optional, defaults to 128) — The head dimension for the QK (query-key) projections when using NOPE (Neural Operator Position Encoding).
qk_rope_head_dim (int, optional, defaults to 64) — The head dimension for QK projections when using RoPE.
routed_scaling_factor (float, optional, defaults to 1.0) — Scaling factor for routed experts in MoE models.
seq_aux (bool, optional, defaults to True) — Whether to compute the auxiliary loss for each individual sequence.
topk_group (int, optional) — Number of selected groups per token for expert selection.
topk_method (str, optional, defaults to "greedy") — The method used for selecting top-k experts in the routed gate mechanism.
v_head_dim (int, optional, defaults to 128) — The dimension of value projections in the attention layers.
num_experts_per_tok (int, optional) — The number of experts selected per token. If None, the model behaves as a dense Transformer.
norm_topk_prob (bool, optional, defaults to False) — Whether to normalize the probability distribution over top-k selected experts.
moe_intermediate_size (int, optional, defaults to 1407) — Dimension of the MoE (Mixture of Experts) representations.

This is the configuration class to store the configuration of a DeepseekV2Model. It is used to instantiate a DeepSeek model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of DeepSeek-V2-Lite” deepseek-ai/DeepSeek-V2-Lite”. Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

>>> from transformers import DeepseekV2Model, DeepseekV2Config
>>> # Initializing a DeepSeek-V2 style configuration
>>> configuration = DeepseekV2Config()
>>> # Accessing the model configuration
>>> model = DeepseekV2Model(configuration)
>>> print(model.config)

DeepseekV2Model

class transformers.DeepseekV2Model

< source >

( config: DeepseekV2Config )

Parameters

config (DeepseekV2Config) — 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 Deepseek V2 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

< source >

( 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 cache_position: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = 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.

Two formats are allowed:
- a Cache instance, see our kv cache guide;
- Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)). This is also known as the legacy cache format.
The model will output the same cache format that is fed as input. If no past_key_values are passed, the legacy cache format will be returned.

If past_key_values are used, the user can optionally input only the last input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) 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.
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.
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

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 (DeepseekV2Config) 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 DeepseekV2Model 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.

DeepseekV2ForCausalLM

class transformers.DeepseekV2ForCausalLM

< source >

( config )

Parameters

config (DeepseekV2ForCausalLM) — 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 Deepseek V2 Model for causal language modeling.

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

< source >

( 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.

Two formats are allowed:
- a Cache instance, see our kv cache guide;
- Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)). This is also known as the legacy cache format.
The model will output the same cache format that is fed as input. If no past_key_values are passed, the legacy cache format will be returned.

If past_key_values are used, the user can optionally input only the last input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) 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 (DeepseekV2Config) 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 DeepseekV2ForCausalLM forward method, overrides the __call__ special method.

Example:

>>> from transformers import AutoTokenizer, DeepseekV2ForCausalLM

>>> model = DeepseekV2ForCausalLM.from_pretrained("meta-deepseek_v2/DeepseekV2-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-deepseek_v2/DeepseekV2-2-7b-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."

DeepseekV2ForSequenceClassification

class transformers.DeepseekV2ForSequenceClassification

< source >

( config )

Parameters

config (DeepseekV2ForSequenceClassification) — 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 DeepseekV2 Model transformer with a sequence classification head on top (linear layer).

DeepseekV2ForSequenceClassification uses the last token in order to do the classification, as other causal models (e.g. GPT-2) do.

Since it does classification on the last token, it requires to know the position of the last token. If a pad_token_id is defined in the configuration, it finds the last token that is not a padding token in each row. If no pad_token_id is defined, it simply takes the last value in each row of the batch. Since it cannot guess the padding tokens when inputs_embeds are passed instead of input_ids, it does the same (take the last value in each row of the batch).

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

< source >

( 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 **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.modeling_outputs.SequenceClassifierOutputWithPast 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.

Two formats are allowed:
- a Cache instance, see our kv cache guide;
- Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)). This is also known as the legacy cache format.
The model will output the same cache format that is fed as input. If no past_key_values are passed, the legacy cache format will be returned.

If past_key_values are used, the user can optionally input only the last input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) 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,), optional) — Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).
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

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

A transformers.modeling_outputs.SequenceClassifierOutputWithPast 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 (DeepseekV2Config) and inputs.

loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.
logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (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 DeepseekV2ForSequenceClassification forward method, overrides the __call__ special method.

Example of single-label classification:

>>> import torch
>>> from transformers import AutoTokenizer, DeepseekV2ForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V2-Lite"")
>>> model = DeepseekV2ForSequenceClassification.from_pretrained("deepseek-ai/DeepSeek-V2-Lite"")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_id = logits.argmax().item()
>>> model.config.id2label[predicted_class_id]
...

>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = DeepseekV2ForSequenceClassification.from_pretrained("deepseek-ai/DeepSeek-V2-Lite"", num_labels=num_labels)

>>> labels = torch.tensor([1])
>>> loss = model(**inputs, labels=labels).loss
>>> round(loss.item(), 2)
...

Example of multi-label classification:

>>> import torch
>>> from transformers import AutoTokenizer, DeepseekV2ForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V2-Lite"")
>>> model = DeepseekV2ForSequenceClassification.from_pretrained("deepseek-ai/DeepSeek-V2-Lite"", problem_type="multi_label_classification")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]

>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = DeepseekV2ForSequenceClassification.from_pretrained(
...     "deepseek-ai/DeepSeek-V2-Lite"", num_labels=num_labels, problem_type="multi_label_classification"
... )

>>> labels = torch.sum(
...     torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1
... ).to(torch.float)
>>> loss = model(**inputs, labels=labels).loss

< > Update on GitHub