transformers/pr_33892/en/model_doc/cohere2.md

Cohere 2

Cohere Command R7B is an open weights research release of a 7B billion parameter model. It is a multilingual model trained on 23 languages and has a context window of 128k. The model features three layers with sliding window attention and ROPE for efficient local context modeling and relative positional encoding. A fourth layer uses global attention without positional embeddings, enabling unrestricted token interactions across the entire sequence.

This model is optimized for speed, cost-performance, and compute resources.

You can find all the original Command-R checkpoints under the Command Models collection.

Click on the Cohere models in the right sidebar for more examples of how to apply Cohere to different language tasks.

The example below demonstrates how to generate text with Pipeline or the AutoModel class, and from the command line.

import torch
from transformers import pipeline

pipeline = pipeline(
    task="text-generation",
    model="CohereLabs/c4ai-command-r7b-12-2024",
    dtype=torch.float16,
    device_map=0
)

messages = [
    {"role": "user", "content": "Hello, can you please help me book a hotel in Japan?"},
]
pipeline(messages)

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CohereLabs/c4ai-command-r7b-12-2024")
model = AutoModelForCausalLM.from_pretrained(
    "CohereLabs/c4ai-command-r7b-12-2024",
    dtype=torch.float16,
    device_map="auto",
    attn_implementation="sdpa"
)

# format message with the Command-R chat template
messages = [{"role": "user", "content": "Hello, can you please help me book a hotel in Japan?"}]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
output = model.generate(
    input_ids,
    max_new_tokens=100,
    do_sample=True,
    temperature=0.3,
    cache_implementation="static",
)
print(tokenizer.decode(output[0], skip_special_tokens=True))

# pip install -U flash-attn --no-build-isolation
transformers chat CohereLabs/c4ai-command-r7b-12-2024 --dtype auto --attn_implementation flash_attention_2

Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the Quantization overview for more available quantization backends.

The example below uses bitsandbytes to quantize the weights to 4-bits.

import torch
from transformers import BitsAndBytesConfig, AutoTokenizer, AutoModelForCausalLM

bnb_config = BitsAndBytesConfig(load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("CohereLabs/c4ai-command-r7b-12-2024")
model = AutoModelForCausalLM.from_pretrained(
    "CohereLabs/c4ai-command-r7b-12-2024",
    dtype=torch.float16,
    device_map="auto",
    quantization_config=bnb_config,
    attn_implementation="sdpa"
)

# format message with the Command-R chat template
messages = [{"role": "user", "content": "Hello, can you please help me book a hotel in Japan?"}]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
output = model.generate(
    input_ids,
    max_new_tokens=100,
    do_sample=True,
    temperature=0.3,
    cache_implementation="static",
)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Cohere2Config[[transformers.Cohere2Config]]

class transformers.Cohere2Configtransformers.Cohere2Confighttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/cohere2/configuration_cohere2.py#L28[{"name": "vocab_size", "val": ": typing.Optional[int] = 256000"}, {"name": "hidden_size", "val": ": typing.Optional[int] = 8192"}, {"name": "intermediate_size", "val": ": typing.Optional[int] = 22528"}, {"name": "logit_scale", "val": ": typing.Optional[float] = 0.0625"}, {"name": "num_hidden_layers", "val": ": typing.Optional[int] = 40"}, {"name": "num_attention_heads", "val": ": typing.Optional[int] = 64"}, {"name": "num_key_value_heads", "val": ": typing.Optional[int] = None"}, {"name": "hidden_act", "val": ": typing.Optional[str] = 'silu'"}, {"name": "max_position_embeddings", "val": ": typing.Optional[int] = 8192"}, {"name": "initializer_range", "val": ": typing.Optional[float] = 0.02"}, {"name": "layer_norm_eps", "val": ": typing.Optional[int] = 1e-05"}, {"name": "use_cache", "val": ": typing.Optional[int] = True"}, {"name": "pad_token_id", "val": ": typing.Optional[int] = 0"}, {"name": "bos_token_id", "val": ": typing.Optional[int] = 5"}, {"name": "eos_token_id", "val": ": typing.Optional[int] = 255001"}, {"name": "tie_word_embeddings", "val": ": typing.Optional[bool] = True"}, {"name": "rope_parameters", "val": ": typing.Union[transformers.modeling_rope_utils.RopeParameters, dict[transformers.modeling_rope_utils.RopeParameters], NoneType] = None"}, {"name": "attention_bias", "val": ": typing.Optional[bool] = False"}, {"name": "attention_dropout", "val": ": typing.Optional[float] = 0.0"}, {"name": "sliding_window", "val": ": typing.Optional[int] = 4096"}, {"name": "layer_types", "val": ": typing.Optional[list[str]] = None"}, {"name": "**kwargs", "val": ""}]- vocab_size (int, optional, defaults to 256000) -- Vocabulary size of the Cohere model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling CohereModel

• hidden_size (int, optional, defaults to 8192) -- Dimension of the hidden representations.
• intermediate_size (int, optional, defaults to 22528) -- Dimension of the MLP representations.
• logit_scale (float, optional, defaults to 0.0625) -- The scaling factor for the output logits.
• num_hidden_layers (int, optional, defaults to 40) -- Number of hidden layers in the Transformer decoder.
• num_attention_heads (int, optional, defaults to 64) -- Number of attention heads for each attention layer in the Transformer decoder.
• num_key_value_heads (int, optional) -- This is the number of key_value heads that should be used to implement Grouped Query Attention. If num_key_value_heads=num_attention_heads, the model will use Multi Head Attention (MHA), if num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details, check out this paper. If it is not specified, will default to num_attention_heads.
• 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 8192) -- 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.
• layer_norm_eps (float, optional, defaults to 1e-05) -- The epsilon used by the layer normalization.
• 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.
• pad_token_id (int, optional, defaults to 0) -- Padding token id.
• bos_token_id (int, optional, defaults to 5) -- Beginning of stream token id.
• eos_token_id (int, optional, defaults to 255001) -- End of stream token id.
• tie_word_embeddings (bool, optional, defaults to True) -- Whether to tie weight embeddings
• rope_parameters (RopeParameters, optional) -- Dictionary containing the configuration parameters for the RoPE embeddings. The dictionaty 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.
• attention_bias (bool, defaults to False, 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 ratio for the attention probabilities.
• sliding_window (int, optional, defaults to 4096) -- Size of the sliding window attention context.
• layer_types (list, optional) -- Attention pattern for each layer.0

This is the configuration class to store the configuration of a CohereModel. It is used to instantiate an Cohere model according to the specified arguments, defining the model architecture.

Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information. Instantiating a configuration with the defaults will yield a similar configuration to that of the CohereForAI/c4ai-command-r-v01 model.

>>> from transformers import Cohere2Model, Cohere2Config

>>> # Initializing a Cohere Nextmodel configuration
>>> configuration = Cohere2Config()

>>> # Initializing a model from the Cohere2 configuration
>>> model = Cohere2Model(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config

Cohere2Model[[transformers.Cohere2Model]]

class transformers.Cohere2Modeltransformers.Cohere2Modelhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/cohere2/modeling_cohere2.py#L365[{"name": "config", "val": ": Cohere2Config"}]- config (Cohere2Config) -- 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.0

The bare Cohere2 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.

forwardtransformers.Cohere2Model.forwardhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/cohere2/modeling_cohere2.py#L382[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "position_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "past_key_values", "val": ": typing.Optional[transformers.cache_utils.Cache] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "use_cache", "val": ": typing.Optional[bool] = None"}, {"name": "cache_position", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

Indices can be obtained using AutoTokenizer. 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.0transformers.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 (Cohere2Config) 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 Cohere2Model 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.

Cohere2ForCausalLM[[transformers.Cohere2ForCausalLM]]

class transformers.Cohere2ForCausalLMtransformers.Cohere2ForCausalLMhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/cohere2/modeling_cohere2.py#L449[{"name": "config", "val": ""}]- config (Cohere2ForCausalLM) -- 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.0

The Cohere2 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.

forwardtransformers.Cohere2ForCausalLM.forwardhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/cohere2/modeling_cohere2.py#L465[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "position_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "past_key_values", "val": ": typing.Optional[transformers.cache_utils.Cache] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "labels", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "use_cache", "val": ": typing.Optional[bool] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "cache_position", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "logits_to_keep", "val": ": typing.Union[int, torch.Tensor] = 0"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

Indices can be obtained using AutoTokenizer. 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).

• output_attentions (bool, optional) -- Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

• output_hidden_states (bool, optional) -- Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

• 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).0transformers.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 (Cohere2Config) 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 Cohere2ForCausalLM 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, Cohere2ForCausalLM

>> model = Cohere2ForCausalLM.from_pretrained("Cohere2ForAI/c4ai-command-r-v01")
>> tokenizer = AutoTokenizer.from_pretrained("Cohere2ForAI/c4ai-command-r-v01")

>> 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."