561820f7ee
- Revert "Move to in-library checkpoint (#81)" (46f48b52085123273538fbbbfc655047720a63d2)
76 lines
2.5 KiB
Python
76 lines
2.5 KiB
Python
# coding=utf-8
|
|
# Copyright 2022 the Big Science Workshop and 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.
|
|
""" Bloom configuration"""
|
|
from transformers.configuration_utils import PretrainedConfig
|
|
from transformers.utils import logging
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
|
|
class RWConfig(PretrainedConfig):
|
|
model_type = "RefinedWeb"
|
|
keys_to_ignore_at_inference = ["past_key_values"]
|
|
attribute_map = {
|
|
"num_hidden_layers": "n_layer",
|
|
"num_attention_heads": "n_head",
|
|
}
|
|
|
|
def __init__(
|
|
self,
|
|
vocab_size=250880,
|
|
hidden_size=64,
|
|
n_layer=2,
|
|
n_head=8,
|
|
layer_norm_epsilon=1e-5,
|
|
initializer_range=0.02,
|
|
use_cache=True,
|
|
bos_token_id=1,
|
|
eos_token_id=2,
|
|
apply_residual_connection_post_layernorm=False,
|
|
hidden_dropout=0.0,
|
|
attention_dropout=0.0,
|
|
n_head_kv=None,
|
|
alibi=False,
|
|
**kwargs,
|
|
):
|
|
self.vocab_size = vocab_size
|
|
# Backward compatibility with n_embed kwarg
|
|
n_embed = kwargs.pop("n_embed", None)
|
|
self.hidden_size = hidden_size if n_embed is None else n_embed
|
|
self.n_layer = n_layer
|
|
self.n_head = n_head
|
|
self.layer_norm_epsilon = layer_norm_epsilon
|
|
self.initializer_range = initializer_range
|
|
self.use_cache = use_cache
|
|
self.apply_residual_connection_post_layernorm = apply_residual_connection_post_layernorm
|
|
self.hidden_dropout = hidden_dropout
|
|
self.attention_dropout = attention_dropout
|
|
|
|
self.bos_token_id = bos_token_id
|
|
self.eos_token_id = eos_token_id
|
|
self.n_head_kv = n_head if n_head_kv is None else n_head_kv
|
|
self.alibi = alibi
|
|
|
|
super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
|
|
|
|
@property
|
|
def head_dim(self):
|
|
return self.hidden_size // self.n_head
|
|
|
|
@property
|
|
def rotary(self):
|
|
return not self.alibi
|