Upload configuration_RW.py with huggingface_hub
Browse files- configuration_RW.py +75 -0
configuration_RW.py
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding=utf-8
|
2 |
+
# Copyright 2022 the Big Science Workshop and HuggingFace Inc. team. All rights reserved.
|
3 |
+
#
|
4 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
+
# you may not use this file except in compliance with the License.
|
6 |
+
# You may obtain a copy of the License at
|
7 |
+
#
|
8 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
+
#
|
10 |
+
# Unless required by applicable law or agreed to in writing, software
|
11 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
+
# See the License for the specific language governing permissions and
|
14 |
+
# limitations under the License.
|
15 |
+
""" Bloom configuration"""
|
16 |
+
from transformers.configuration_utils import PretrainedConfig
|
17 |
+
from transformers.utils import logging
|
18 |
+
|
19 |
+
|
20 |
+
logger = logging.get_logger(__name__)
|
21 |
+
|
22 |
+
|
23 |
+
class RWConfig(PretrainedConfig):
|
24 |
+
model_type = "RefinedWeb"
|
25 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
26 |
+
attribute_map = {
|
27 |
+
"num_hidden_layers": "n_layer",
|
28 |
+
"num_attention_heads": "n_head",
|
29 |
+
}
|
30 |
+
|
31 |
+
def __init__(
|
32 |
+
self,
|
33 |
+
vocab_size=250880,
|
34 |
+
hidden_size=64,
|
35 |
+
n_layer=2,
|
36 |
+
n_head=8,
|
37 |
+
layer_norm_epsilon=1e-5,
|
38 |
+
initializer_range=0.02,
|
39 |
+
use_cache=True,
|
40 |
+
bos_token_id=1,
|
41 |
+
eos_token_id=2,
|
42 |
+
apply_residual_connection_post_layernorm=False,
|
43 |
+
hidden_dropout=0.0,
|
44 |
+
attention_dropout=0.0,
|
45 |
+
n_head_kv=None,
|
46 |
+
alibi=False,
|
47 |
+
**kwargs,
|
48 |
+
):
|
49 |
+
self.vocab_size = vocab_size
|
50 |
+
# Backward compatibility with n_embed kwarg
|
51 |
+
n_embed = kwargs.pop("n_embed", None)
|
52 |
+
self.hidden_size = hidden_size if n_embed is None else n_embed
|
53 |
+
self.n_layer = n_layer
|
54 |
+
self.n_head = n_head
|
55 |
+
self.layer_norm_epsilon = layer_norm_epsilon
|
56 |
+
self.initializer_range = initializer_range
|
57 |
+
self.use_cache = use_cache
|
58 |
+
self.apply_residual_connection_post_layernorm = apply_residual_connection_post_layernorm
|
59 |
+
self.hidden_dropout = hidden_dropout
|
60 |
+
self.attention_dropout = attention_dropout
|
61 |
+
|
62 |
+
self.bos_token_id = bos_token_id
|
63 |
+
self.eos_token_id = eos_token_id
|
64 |
+
self.n_head_kv = n_head if n_head_kv is None else n_head_kv
|
65 |
+
self.alibi = alibi
|
66 |
+
|
67 |
+
super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
|
68 |
+
|
69 |
+
@property
|
70 |
+
def head_dim(self):
|
71 |
+
return self.hidden_size // self.n_head
|
72 |
+
|
73 |
+
@property
|
74 |
+
def rotary(self):
|
75 |
+
return not self.alibi
|