File size: 10,133 Bytes
91b3b8c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 |
# coding=utf-8
# Copyright 2025 Arcee AI and the HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""PyTorch Arcee model."""
from transformers.utils import auto_docstring, logging
from ..llama.configuration_llama import LlamaConfig
from ..llama.modeling_llama import (
LlamaForCausalLM,
LlamaForQuestionAnswering,
LlamaForSequenceClassification,
LlamaForTokenClassification,
)
from ..nemotron.modeling_nemotron import NemotronMLP
logger = logging.get_logger(__name__)
class ArceeConfig(LlamaConfig):
r"""
This is the configuration class to store the configuration of a [`ArceeModel`]. It is used to instantiate an Arcee
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 AFM-4.5B-Base.
Pre-trained weights are available at
[arcee-ai/AFM-4.5B](https://huggingface.co/arcee-ai/AFM-4.5B)
and were used to build the examples below.
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.
Args:
vocab_size (`int`, *optional*, defaults to 32000):
Vocabulary size of the Arcee model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`ArceeModel`]
hidden_size (`int`, *optional*, defaults to 2560):
Dimension of the hidden representations.
intermediate_size (`int`, *optional*, defaults to 18432):
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*):
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 checkout [this
paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to
`num_attention_heads`.
hidden_act (`str` or `function`, *optional*, defaults to `"relu2"`):
The non-linear activation function (function or string) in the decoder.
max_position_embeddings (`int`, *optional*, defaults to 4096):
The maximum sequence length that this model might ever be used with. AFM-4.5B-Base supports up to 16384 tokens.
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`.
pad_token_id (`int`, *optional*):
Padding token id.
bos_token_id (`int`, *optional*, defaults to 128000):
Beginning of stream token id.
eos_token_id (`int`, *optional*, defaults to 128001):
End of stream token id.
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
Whether to tie weight embeddings
rope_theta (`float`, *optional*, defaults to 10000.0):
The base period of the RoPE embeddings.
rope_scaling (`Dict`, *optional*):
Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
accordingly.
Expected contents:
`rope_type` (`str`):
The sub-variant of RoPE to use. Can be one of ['default', 'yarn'], with 'default' being the original RoPE implementation.
`factor` (`float`, *optional*):
Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
most scaling types, a `factor` of x will enable the model to handle sequences of length x *
original maximum pre-trained length.
`original_max_position_embeddings` (`int`, *optional*):
Used with 'yarn'. The original max position embeddings used during pretraining.
`attention_factor` (`float`, *optional*):
Used with 'yarn'. The scaling factor to be applied on the attention computation. If unspecified,
it defaults to value recommended by the implementation, using the `factor` field to infer the suggested value.
`beta_fast` (`float`, *optional*):
Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
ramp function. If unspecified, it defaults to 32.
`beta_slow` (`float`, *optional*):
Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
ramp function. If unspecified, it defaults to 1.
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 ratio for the attention probabilities.
mlp_bias (`bool`, *optional*, defaults to `False`):
Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers.
head_dim (`int`, *optional*):
The attention head dimension. If None, it will default to hidden_size // num_attention_heads
```python
>>> from transformers import ArceeModel, ArceeConfig
>>> # Initializing an Arcee AFM-4.5B-Base style configuration
>>> configuration = ArceeConfig()
>>> # Initializing a model from the AFM-4.5B-Base style configuration
>>> model = ArceeModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "arcee"
base_model_tp_plan = {
"layers.*.self_attn.q_proj": "colwise",
"layers.*.self_attn.k_proj": "colwise",
"layers.*.self_attn.v_proj": "colwise",
"layers.*.self_attn.o_proj": "rowwise",
"layers.*.mlp.up_proj": "colwise",
"layers.*.mlp.down_proj": "rowwise",
}
def __init__(
self,
vocab_size=32000,
hidden_size=2560,
intermediate_size=18432,
num_hidden_layers=32,
num_attention_heads=32,
num_key_value_heads=None,
hidden_act="relu2",
max_position_embeddings=4096,
initializer_range=0.02,
rms_norm_eps=1e-5,
use_cache=True,
pad_token_id=None,
bos_token_id=128000,
eos_token_id=128001,
tie_word_embeddings=False,
rope_theta=10000.0,
rope_scaling=None,
attention_bias=False,
attention_dropout=0.0,
mlp_bias=False,
head_dim=None,
**kwargs,
):
super().__init__(
vocab_size=vocab_size,
hidden_size=hidden_size,
intermediate_size=intermediate_size,
num_hidden_layers=num_hidden_layers,
num_attention_heads=num_attention_heads,
num_key_value_heads=num_key_value_heads,
hidden_act=hidden_act,
max_position_embeddings=max_position_embeddings,
initializer_range=initializer_range,
rms_norm_eps=rms_norm_eps,
use_cache=use_cache,
pad_token_id=pad_token_id,
bos_token_id=bos_token_id,
eos_token_id=eos_token_id,
tie_word_embeddings=tie_word_embeddings,
rope_theta=rope_theta,
rope_scaling=rope_scaling,
attention_bias=attention_bias,
attention_dropout=attention_dropout,
mlp_bias=mlp_bias,
head_dim=head_dim,
**kwargs,
)
del self.pretraining_tp
class ArceeMLP(NemotronMLP):
pass
@auto_docstring(checkpoint="arcee-ai/AFM-4.5B")
class ArceeForCausalLM(LlamaForCausalLM):
pass
@auto_docstring(checkpoint="arcee-ai/AFM-4.5B")
class ArceeForSequenceClassification(LlamaForSequenceClassification):
pass
@auto_docstring(checkpoint="arcee-ai/AFM-4.5B")
class ArceeForQuestionAnswering(LlamaForQuestionAnswering):
pass
@auto_docstring(checkpoint="arcee-ai/AFM-4.5B")
class ArceeForTokenClassification(LlamaForTokenClassification):
pass
__all__ = [
"ArceeConfig",
"ArceeForCausalLM",
"ArceeForQuestionAnswering",
"ArceeForSequenceClassification",
"ArceeForTokenClassification",
"ArceeModel", # noqa: F822
"ArceePreTrainedModel", # noqa: F822
]
|