biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Re-enable the 80 char line width limit (#3305)

Browse Source
This commit is contained in:
Zhuohan Li
2024-03-10 19:49:14 -07:00
committed by GitHub
parent 4b59f00e91
commit 2f8844ba08
67 changed files with 557 additions and 528 deletions
Download Patch File Download Diff File Expand all files Collapse all files

72
vllm/transformers_utils/configs/starcoder2.py
View File

@@ -2,78 +2,6 @@ from transformers import PretrainedConfig
class Starcoder2Config(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`Starcoder2Model`]. It is used to instantiate a
Starcoder2 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 [bigcode/starcoder2-7b_16k](https://huggingface.co/bigcode/starcoder2-7b_16k) model.
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 49152):
Vocabulary size of the Starcoder2 model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`Starcoder2Model`]
hidden_size (`int`, *optional*, defaults to 3072):
Dimension of the hidden representations.
intermediate_size (`int`, *optional*, defaults to 12288):
Dimension of the MLP representations.
num_hidden_layers (`int`, *optional*, defaults to 30):
Number of hidden layers in the Transformer encoder.
num_attention_heads (`int`, *optional*, defaults to 24):
Number of attention heads for each attention layer in the Transformer encoder.
num_key_value_heads (`int`, *optional*, defaults to 2):
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://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `8`.
hidden_act (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`):
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. Starcoder2's sliding window attention
allows sequence of up to 4096*32 tokens.
initializer_range (`float`, *optional*, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
norm_epsilon (`float`, *optional*, defaults to 1e-05):
Epsilon value for the layer norm
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`.
bos_token_id (`int`, *optional*, defaults to 50256):
The id of the "beginning-of-sequence" token.
eos_token_id (`int`, *optional*, defaults to 50256):
The id of the "end-of-sequence" token.
rope_theta (`float`, *optional*, defaults to 10000.0):
The base period of the RoPE embeddings.
sliding_window (`int`, *optional*):
Sliding window attention window size. If not specified, will default to `None` (no sliding window).
attention_dropout (`float`, *optional*, defaults to 0.0):
The dropout ratio for the attention probabilities.
residual_dropout (`float`, *optional*, defaults to 0.0):
Residual connection dropout value.
embedding_dropout (`float`, *optional*, defaults to 0.0):
Embedding dropout.
use_bias (`bool`, *optional*, defaults to `True`):
Whether to use bias term on linear layers of the model.
```python
>>> from transformers import Starcoder2Model, Starcoder2Config
>>> # Initializing a Starcoder2 7B style configuration
>>> configuration = Starcoder2Config()
>>> # Initializing a model from the Starcoder2 7B style configuration
>>> model = Starcoder2Model(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "starcoder2"
keys_to_ignore_at_inference = ["past_key_values"]