Zamba2 is a large language model (LLM) trained by Zyphra, and made available under an Apache 2.0 license. Please see the Zyphra Hugging Face repository for model weights.
This model was contributed by pglo.
Model detailsZamba2-1.2B, Zamba2-2.7B and Zamba2-7B are hybrid models combining state-space models (Specifically Mamba) and transformer, and were trained using next-token prediction. Zamba2 uses shared transformer layers after every 6 mamba blocks. It uses the Mistral v0.1 tokenizer. We came to this architecture after a series of ablations at small scales. Zamba2-1.2B, Zamba2-2.7B and Zamba2-7B were pre-trained on 2T and 3T tokens, respectively.
Quick start PresequitiesZamba2 requires you use transformers version 4.48.0 or higher:
pip install transformers>=4.48.0Inference
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-7B")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-7B", device_map="cuda", torch_dtype=torch.bfloat16)
input_text = "What factors contributed to the fall of the Roman Empire?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0])) Model card
The model cards can be found at:
IssuesFor issues with model output, or community discussion, please use the Hugging Face community forum
LicenseThe model weights are open-sourced via an Apache 2.0 license.
Zamba2Config class transformers.Zamba2Config < source >( vocab_size = 32000 max_position_embeddings = 4096 hidden_size = 2560 num_hidden_layers = 54 layers_block_type = None mamba_d_state = 64 mamba_d_conv = 4 mamba_expand = 2 mamba_ngroups = 1 time_step_min = 0.001 time_step_max = 0.1 time_step_floor = 0.0001 time_step_limit = None n_mamba_heads = 8 use_conv_bias = True chunk_size = 256 use_mem_eff_path = False add_bias_linear = False intermediate_size = None hidden_act = 'gelu' num_attention_heads = 32 num_key_value_heads = None attention_dropout = 0.0 num_mem_blocks = 1 use_shared_attention_adapter = False adapter_rank = 128 use_mem_rope = False rope_theta = 10000 initializer_range = 0.02 rms_norm_eps = 1e-05 use_cache = True num_logits_to_keep = 1 pad_token_id = 0 bos_token_id = 1 eos_token_id = 2 use_long_context = False **kwargs )
Parameters
int, optional, defaults to 32000) — Vocabulary size of the Zamba2 model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling Zamba2Model int, optional, defaults to 4096) — The maximum sequence length that this model might ever be used with. int, optional, defaults to 2560) — Dimension of the hidden representations. int, optional, defaults to 54) — Number of hidden layers in the model. list, optional) — List of layer types, which can be either “mamba” or “hybrid”. int, optional, defaults to 64) — shape of the state space latents. int, optional, defaults to 4) — Size of the convolution kernel. int, optional, defaults to 2) — Expanding factor used to determine the intermediate size. int, optional, defaults to 1) — Number of groups for the evolution matrices of mamba 2. float, optional, defaults to 0.001) — Minimum time_step used to bound dt_proj.bias. float, optional, defaults to 0.1) — Maximum time_step used to bound dt_proj.bias. float, optional, defaults to 0.0001) — Minimum clamping value of the dt_proj.bias layer initialization. tuple, optional) — Accepted range of time step values. int, optional, defaults to 8) — Number of heads for the evolution matrices of mamba 2. bool, optional, defaults to True) — Whether or not to use bias in the convolution layer of the mixer block. int, optional, defaults to 256) — Size of the chunks that will comprise the sequence. bool, optional, defaults to False) — Whether or not to use the fused conv1d and scan in mamba2 layers. bool, optional, defaults to False) — Flag indicating whether or not to use bias in various layers int, optional, defaults to 4 * hidden_size) — Dimension of the MLP representations. str, optional, defaults to "gelu") — The non-linear activation function (function or string) in the MLP. int, optional, defaults to 32) — Number of attention heads for each attention layer in the Transformer decoder. int, optional) — This is the number of key_value heads that should be used to implement Grouped Query Attention. If num_key_value_heads=None, 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 checkout this paper. float, optional, defaults to 0.0) — The dropout ratio for the attention probabilities. int, optional, defaults to 1) — Number of unshared transformer blocks. bool, optional, defaults to False) — If True, unshared adapters (formally the same as LoRA but used in the base model) will be added to the q, k, v projectors in the shared attention layers. int, optional, defaults to 128) — Rank of the adapter in the shared MLP and shared attention layers. bool, optional, defaults to False) — If True, includes RoPE in the shared attention layers. float, optional, defaults to 10000.0) — The base period of the RoPE embeddings. float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices. float, optional, defaults to 1e-05) — The epsilon used by the rms normalization layers. 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. int or None, optional, defaults to 1) — Number of prompt logits to calculate during generation. If None, all logits will be calculated. If an integer value, only last num_logits_to_keep logits will be calculated. Default is 1 because only the logits of the last prompt token are needed for generation. For long sequences, the logits for the entire sequence may use a lot of memory so, setting num_logits_to_keep=1 will reduce memory footprint significantly. int, optional, defaults to 0) — The id of the padding token. int, optional, defaults to 1) — The id of the “beginning-of-sequence” token. int, optional, defaults to 2) — The id of the “end-of-sequence” token. bool, optional, defaults to False) — Activates the context-extended version of Zamba by modifying RoPE. This is the configuration class to store the configuration of a Zamba2Model. It is used to instantiate a Zamba2 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 Zamba2 model.
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 Zamba2Model, Zamba2Config >>> >>> configuration = Zamba2Config() >>> >>> model = Zamba2Model(configuration) >>> >>> configuration = model.configZamba2Model class transformers.Zamba2Model < source >
( config: Zamba2Config )
Parameters
The bare Zamba2 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.
Model consisting of config.num_hidden_layers layers.
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.models.zamba2.modeling_zamba2.Zamba2HybridDynamicCache] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None cache_position: typing.Optional[torch.LongTensor] = None )
Parameters
torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.
Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
torch.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
If past_key_values is used, optionally only the last input_ids have to be input (see past_key_values).
If you want to change padding behavior, you should read modeling_opt._prepare_decoder_attention_mask and modify to your needs. See diagram 1 in the paper for more information on the default strategy.
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].
Zamba2HybridDynamicCache, optional, returned when use_cache=True is passed or when config.use_cache=True) — A Zamba2HybridDynamicCache object containing pre-computed hidden-states (keys and values in the self-attention blocks and convolution and ssm states in the mamba blocks) that can be used (see past_key_values input) to speed up sequential decoding. Key and value cache tensors have shape (batch_size, num_heads, seq_len, head_dim). Convolution and ssm states tensors have shape (batch_size, d_inner, d_conv) and (batch_size, d_inner, d_state) respectively. See the Zamba2HybridDynamicCache class for more details.
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).
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. 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). bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. 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. The Zamba2Model 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.
( config: Zamba2Config )
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.models.zamba2.modeling_zamba2.Zamba2HybridDynamicCache] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None cache_position: typing.Optional[torch.LongTensor] = None logits_to_keep: typing.Union[int, torch.Tensor] = 0 **loss_kwargs ) → transformers.modeling_outputs.CausalLMOutputWithPast or tuple(torch.FloatTensor)
Parameters
torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.
Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
torch.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
If past_key_values is used, optionally only the last input_ids have to be input (see past_key_values).
If you want to change padding behavior, you should read modeling_opt._prepare_decoder_attention_mask and modify to your needs. See diagram 1 in the paper for more information on the default strategy.
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].
Zamba2HybridDynamicCache, optional, returned when use_cache=True is passed or when config.use_cache=True) — A Zamba2HybridDynamicCache object containing pre-computed hidden-states (keys and values in the self-attention blocks and convolution and ssm states in the mamba blocks) that can be used (see past_key_values input) to speed up sequential decoding. Key and value cache tensors have shape (batch_size, num_heads, seq_len, head_dim). Convolution and ssm states tensors have shape (batch_size, d_inner, d_conv) and (batch_size, d_inner, d_state) respectively. See the Zamba2HybridDynamicCache class for more details.
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).
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. 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). bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. 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. 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]. int or torch.Tensor, optional) — 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). 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 (Zyphra/Zamba2-2.7B) 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 (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — 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))
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 Zamba2ForCausalLM 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, Zamba2ForCausalLM
>>> model = Zamba2ForCausalLM.from_pretrained("Zyphra/Zamba2-7B-v1")
>>> tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-7B-v1")
>>> prompt = "Hey, are you conscious? Can you talk to me?"
>>> inputs = tokenizer(prompt, return_tensors="pt")
>>>
>>> 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." Zamba2ForSequenceClassification class transformers.Zamba2ForSequenceClassification < source >
( config )
Parameters
The Zamba2 Model with a sequence classification head on top (linear layer).
Zamba2ForSequenceClassification 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 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.Union[transformers.cache_utils.Cache, typing.List[torch.FloatTensor], NoneType] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None )
Parameters
torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.
Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
torch.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
If past_key_values is used, optionally only the last input_ids have to be input (see past_key_values).
If you want to change padding behavior, you should read modeling_opt._prepare_decoder_attention_mask and modify to your needs. See diagram 1 in the paper for more information on the default strategy.
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].
Zamba2HybridDynamicCache, optional, returned when use_cache=True is passed or when config.use_cache=True) — A Zamba2HybridDynamicCache object containing pre-computed hidden-states (keys and values in the self-attention blocks and convolution and ssm states in the mamba blocks) that can be used (see past_key_values input) to speed up sequential decoding. Key and value cache tensors have shape (batch_size, num_heads, seq_len, head_dim). Convolution and ssm states tensors have shape (batch_size, d_inner, d_conv) and (batch_size, d_inner, d_state) respectively. See the Zamba2HybridDynamicCache class for more details.
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).
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. 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). bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. 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. 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). The Zamba2ForSequenceClassification 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.
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.3