Commit
•
9236b96
1
Parent(s):
2e6a614
Upload 11 files
Browse files- LICENSE +190 -0
- README.md +71 -3
- RewardModel_emissions.csv +2 -0
- config.json +30 -0
- pytorch_model.bin +3 -0
- reward_model.py +44 -0
- reward_model_config.py +46 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- vocab.txt +0 -0
LICENSE
ADDED
@@ -0,0 +1,190 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Apache License
|
2 |
+
Version 2.0, January 2004
|
3 |
+
http://www.apache.org/licenses/
|
4 |
+
|
5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
6 |
+
|
7 |
+
1. Definitions.
|
8 |
+
|
9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
11 |
+
|
12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
13 |
+
the copyright owner that is granting the License.
|
14 |
+
|
15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
16 |
+
other entities that control, are controlled by, or are under common
|
17 |
+
control with that entity. For the purposes of this definition,
|
18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
19 |
+
direction or management of such entity, whether by contract or
|
20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
22 |
+
|
23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
24 |
+
exercising permissions granted by this License.
|
25 |
+
|
26 |
+
"Source" form shall mean the preferred form for making modifications,
|
27 |
+
including but not limited to software source code, documentation
|
28 |
+
source, and configuration files.
|
29 |
+
|
30 |
+
"Object" form shall mean any form resulting from mechanical
|
31 |
+
transformation or translation of a Source form, including but
|
32 |
+
not limited to compiled object code, generated documentation,
|
33 |
+
and conversions to other media types.
|
34 |
+
|
35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
36 |
+
Object form, made available under the License, as indicated by a
|
37 |
+
copyright notice that is included in or attached to the work
|
38 |
+
(an example is provided in the Appendix below).
|
39 |
+
|
40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
41 |
+
form, that is based on (or derived from) the Work and for which the
|
42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
44 |
+
of this License, Derivative Works shall not include works that remain
|
45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
46 |
+
the Work and Derivative Works thereof.
|
47 |
+
|
48 |
+
"Contribution" shall mean any work of authorship, including
|
49 |
+
the original version of the Work and any modifications or additions
|
50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
54 |
+
means any form of electronic, verbal, or written communication sent
|
55 |
+
to the Licensor or its representatives, including but not limited to
|
56 |
+
communication on electronic mailing lists, source code control systems,
|
57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
59 |
+
excluding communication that is conspicuously marked or otherwise
|
60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
61 |
+
|
62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
64 |
+
subsequently incorporated within the Work.
|
65 |
+
|
66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
71 |
+
Work and such Derivative Works in Source or Object form.
|
72 |
+
|
73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
76 |
+
(except as stated in this section) patent license to make, have made,
|
77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
78 |
+
where such license applies only to those patent claims licensable
|
79 |
+
by such Contributor that are necessarily infringed by their
|
80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
82 |
+
institute patent litigation against any entity (including a
|
83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
84 |
+
or a Contribution incorporated within the Work constitutes direct
|
85 |
+
or contributory patent infringement, then any patent licenses
|
86 |
+
granted to You under this License for that Work shall terminate
|
87 |
+
as of the date such litigation is filed.
|
88 |
+
|
89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
90 |
+
Work or Derivative Works thereof in any medium, with or without
|
91 |
+
modifications, and in Source or Object form, provided that You
|
92 |
+
meet the following conditions:
|
93 |
+
|
94 |
+
(a) You must give any other recipients of the Work or
|
95 |
+
Derivative Works a copy of this License; and
|
96 |
+
|
97 |
+
(b) You must cause any modified files to carry prominent notices
|
98 |
+
stating that You changed the files; and
|
99 |
+
|
100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
101 |
+
that You distribute, all copyright, patent, trademark, and
|
102 |
+
attribution notices from the Source form of the Work,
|
103 |
+
excluding those notices that do not pertain to any part of
|
104 |
+
the Derivative Works; and
|
105 |
+
|
106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
107 |
+
distribution, then any Derivative Works that You distribute must
|
108 |
+
include a readable copy of the attribution notices contained
|
109 |
+
within such NOTICE file, excluding those notices that do not
|
110 |
+
pertain to any part of the Derivative Works, in at least one
|
111 |
+
of the following places: within a NOTICE text file distributed
|
112 |
+
as part of the Derivative Works; within the Source form or
|
113 |
+
documentation, if provided along with the Derivative Works; or,
|
114 |
+
within a display generated by the Derivative Works, if and
|
115 |
+
wherever such third-party notices normally appear. The contents
|
116 |
+
of the NOTICE file are for informational purposes only and
|
117 |
+
do not modify the License. You may add Your own attribution
|
118 |
+
notices within Derivative Works that You distribute, alongside
|
119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
120 |
+
that such additional attribution notices cannot be construed
|
121 |
+
as modifying the License.
|
122 |
+
|
123 |
+
You may add Your own copyright statement to Your modifications and
|
124 |
+
may provide additional or different license terms and conditions
|
125 |
+
for use, reproduction, or distribution of Your modifications, or
|
126 |
+
for any such Derivative Works as a whole, provided Your use,
|
127 |
+
reproduction, and distribution of the Work otherwise complies with
|
128 |
+
the conditions stated in this License.
|
129 |
+
|
130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
132 |
+
by You to the Licensor shall be under the terms and conditions of
|
133 |
+
this License, without any additional terms or conditions.
|
134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
135 |
+
the terms of any separate license agreement you may have executed
|
136 |
+
with Licensor regarding such Contributions.
|
137 |
+
|
138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
140 |
+
except as required for reasonable and customary use in describing the
|
141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
142 |
+
|
143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
144 |
+
agreed to in writing, Licensor provides the Work (and each
|
145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
147 |
+
implied, including, without limitation, any warranties or conditions
|
148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
150 |
+
appropriateness of using or redistributing the Work and assume any
|
151 |
+
risks associated with Your exercise of permissions under this License.
|
152 |
+
|
153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
154 |
+
whether in tort (including negligence), contract, or otherwise,
|
155 |
+
unless required by applicable law (such as deliberate and grossly
|
156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
157 |
+
liable to You for damages, including any direct, indirect, special,
|
158 |
+
incidental, or consequential damages of any character arising as a
|
159 |
+
result of this License or out of the use or inability to use the
|
160 |
+
Work (including but not limited to damages for loss of goodwill,
|
161 |
+
work stoppage, computer failure or malfunction, or any and all
|
162 |
+
other commercial damages or losses), even if such Contributor
|
163 |
+
has been advised of the possibility of such damages.
|
164 |
+
|
165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
168 |
+
or other liability obligations and/or rights consistent with this
|
169 |
+
License. However, in accepting such obligations, You may act only
|
170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
171 |
+
of any other Contributor, and only if You agree to indemnify,
|
172 |
+
defend, and hold each Contributor harmless for any liability
|
173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
174 |
+
of your accepting any such warranty or additional liability.
|
175 |
+
|
176 |
+
END OF TERMS AND CONDITIONS
|
177 |
+
|
178 |
+
Copyright Nicholas Kluge Corrêa
|
179 |
+
|
180 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
181 |
+
you may not use this file except in compliance with the License.
|
182 |
+
You may obtain a copy of the License at
|
183 |
+
|
184 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
185 |
+
|
186 |
+
Unless required by applicable law or agreed to in writing, software
|
187 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
188 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
189 |
+
See the License for the specific language governing permissions and
|
190 |
+
limitations under the License.
|
README.md
CHANGED
@@ -1,3 +1,71 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# RewardModel (Portuguese-BR)
|
2 |
+
|
3 |
+
The `RewardModel` is a modified BERT model that can be used to score the quality of completion to a given prompt. It is based on the [BERT](https://huggingface.co/bert-base-cased), modified to act as a regression model.
|
4 |
+
|
5 |
+
The `RewardModel` allows the specification of an $\alpha$ parameter, which is a multiplier to the reward score. This multiplier is set to 1 during training (since our reward values are bounded between -1 and 1) but can be changed at inference to allow for rewards with higher bounds.
|
6 |
+
|
7 |
+
The model was trained with a dataset composed of `prompt`, `completions`, and annotated `rewards`.
|
8 |
+
|
9 |
+
> Note: These prompt + completions are samples of intruction datasets created via the [Self-Instruct](https://github.com/yizhongw/self-instruct) framework.
|
10 |
+
|
11 |
+
## Usage
|
12 |
+
|
13 |
+
Here's an example of how to use the `RewardModelPT` to score the quality of a response to a given prompt:
|
14 |
+
|
15 |
+
```python
|
16 |
+
from transformers import AutoTokenizer,AutoConfig, AutoModel
|
17 |
+
import torch
|
18 |
+
|
19 |
+
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
20 |
+
|
21 |
+
config = AutoConfig.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, revision='main')
|
22 |
+
tokenizer = AutoTokenizer.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, config=config, revision='main')
|
23 |
+
rewardModel = AutoModel.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, config=config, revision='main')
|
24 |
+
|
25 |
+
rewardModel.to(device)
|
26 |
+
rewardModel.eval()
|
27 |
+
|
28 |
+
|
29 |
+
# Define the question and response
|
30 |
+
question = "What is the capital of France?"
|
31 |
+
response1 = "Paris, France's capital, is a major European city and a global center for art, fashion, gastronomy and culture."
|
32 |
+
response2 = "Google it pal."
|
33 |
+
|
34 |
+
# Tokenize the question and response
|
35 |
+
tokens = tokenizer(question, response1,
|
36 |
+
return_token_type_ids=False,
|
37 |
+
return_tensors="pt",
|
38 |
+
return_attention_mask=True)
|
39 |
+
|
40 |
+
tokens.to(device)
|
41 |
+
|
42 |
+
# Score the response
|
43 |
+
score = model(**tokens, alpha=10).item()
|
44 |
+
|
45 |
+
print(f"Question: {question} \n")
|
46 |
+
print(f"Response 1: {response1} Score: {score:.3f}")
|
47 |
+
|
48 |
+
tokens = tokenizer(question, response2,
|
49 |
+
return_token_type_ids=False,
|
50 |
+
return_tensors="pt",
|
51 |
+
return_attention_mask=True)
|
52 |
+
|
53 |
+
tokens.to(device)
|
54 |
+
|
55 |
+
score = model(**tokens, alpha=10).item()
|
56 |
+
|
57 |
+
print(f"Response 2: {response2} Score: {score:.3f}")
|
58 |
+
```
|
59 |
+
|
60 |
+
This will output the following:
|
61 |
+
|
62 |
+
```markdown
|
63 |
+
>>> Question: What is the capital of France?
|
64 |
+
|
65 |
+
>>>Response: Paris, France's capital, is a major European city and a global center for art, fashion, gastronomy and culture. Score: 3.183
|
66 |
+
>>>Response: Google it pal. Score: -5.781
|
67 |
+
```
|
68 |
+
|
69 |
+
## License
|
70 |
+
|
71 |
+
The `RewardModelPT` is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
|
RewardModel_emissions.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
2 |
+
2023-06-06T23:21:22,RewardModel_emissions,767a1dcb-8c17-468e-99a1-f8cb8a573764,5520.023492097855,0.2112234791927602,3.826496019358169e-05,42.5,367.288,31.30528450012207,0.06516678402125839,0.49168802718218657,0.047978027476773516,0.6048328386802171,United States,USA,nevada,,,Linux-5.15.107+-x86_64-with-glibc2.31,3.10.11,2.2.3,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,-115.1164,36.1685,83.48075866699219,machine,N,1.0
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"RewardModel"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"auto_map": {
|
7 |
+
"AutoConfig": "reward_model_config.RewardModelConfig",
|
8 |
+
"AutoModel": "reward_model.RewardModel"
|
9 |
+
},
|
10 |
+
"classifier_dropout": null,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-12,
|
17 |
+
"linear_layer": 128,
|
18 |
+
"linear_layer_output": 1,
|
19 |
+
"max_position_embeddings": 512,
|
20 |
+
"model_type": "bert-reward",
|
21 |
+
"num_attention_heads": 12,
|
22 |
+
"num_hidden_layers": 12,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"position_embedding_type": "absolute",
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.25.1",
|
27 |
+
"type_vocab_size": 2,
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 28996
|
30 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea3a11bda31a8c8112131c41c7480284f254d1599c3a2a0880dba044da7821df
|
3 |
+
size 433770725
|
reward_model.py
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import BertPreTrainedModel, BertModel, BertConfig
|
2 |
+
from .reward_model_config import RewardModelConfig
|
3 |
+
import torch
|
4 |
+
|
5 |
+
class RewardModel(BertPreTrainedModel):
|
6 |
+
"""
|
7 |
+
RewardModel class for PyTorch
|
8 |
+
|
9 |
+
Args:
|
10 |
+
config (transformers.configuration): model configuration
|
11 |
+
|
12 |
+
Returns:
|
13 |
+
output (torch.tensor): tensor containing the output logits [-1,1]
|
14 |
+
"""
|
15 |
+
config_class = RewardModelConfig
|
16 |
+
|
17 |
+
def __init__(self, config):
|
18 |
+
super().__init__(config)
|
19 |
+
self.bert = BertModel(config)
|
20 |
+
|
21 |
+
self.cls_layer1 = torch.nn.Linear(config.hidden_size,config.linear_layer)
|
22 |
+
self.relu1 = torch.nn.ReLU()
|
23 |
+
self.ff1 = torch.nn.Linear(config.linear_layer,config.linear_layer)
|
24 |
+
self.tanh1 = torch.nn.Tanh()
|
25 |
+
self.ff2 = torch.nn.Linear(config.linear_layer,config.linear_layer_output)
|
26 |
+
|
27 |
+
def forward(self, input_ids, attention_mask, alpha=1):
|
28 |
+
|
29 |
+
outputs = self.bert(input_ids=input_ids, attention_mask=attention_mask)
|
30 |
+
|
31 |
+
logits = outputs.last_hidden_state[:,0,:]
|
32 |
+
output = self.cls_layer1(logits)
|
33 |
+
output = self.relu1(output)
|
34 |
+
output = self.ff1(output)
|
35 |
+
output = self.tanh1(output)
|
36 |
+
output = self.ff2(output)
|
37 |
+
|
38 |
+
# Apply alpha and beta to output (if not training)
|
39 |
+
if not self.training:
|
40 |
+
|
41 |
+
# alpha multiplies the output by a scalar
|
42 |
+
output = torch.mul(output, alpha)
|
43 |
+
|
44 |
+
return output
|
reward_model_config.py
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import PretrainedConfig
|
2 |
+
|
3 |
+
class RewardModelConfig(PretrainedConfig):
|
4 |
+
model_type="bert-reward"
|
5 |
+
|
6 |
+
def __init__(
|
7 |
+
self,
|
8 |
+
vocab_size=28996,
|
9 |
+
hidden_size=768,
|
10 |
+
num_hidden_layers=12,
|
11 |
+
num_attention_heads=12,
|
12 |
+
intermediate_size=3072,
|
13 |
+
hidden_act="gelu",
|
14 |
+
hidden_dropout_prob=0.1,
|
15 |
+
attention_probs_dropout_prob=0.1,
|
16 |
+
max_position_embeddings=512,
|
17 |
+
type_vocab_size=2,
|
18 |
+
initializer_range=0.02,
|
19 |
+
layer_norm_eps=1e-12,
|
20 |
+
pad_token_id=0,
|
21 |
+
position_embedding_type="absolute",
|
22 |
+
use_cache=True,
|
23 |
+
classifier_dropout=None,
|
24 |
+
linear_layer=128,
|
25 |
+
linear_layer_output=1,
|
26 |
+
**kwargs,
|
27 |
+
):
|
28 |
+
super().__init__(pad_token_id=pad_token_id, **kwargs)
|
29 |
+
|
30 |
+
self.vocab_size = vocab_size
|
31 |
+
self.hidden_size = hidden_size
|
32 |
+
self.num_hidden_layers = num_hidden_layers
|
33 |
+
self.num_attention_heads = num_attention_heads
|
34 |
+
self.hidden_act = hidden_act
|
35 |
+
self.intermediate_size = intermediate_size
|
36 |
+
self.hidden_dropout_prob = hidden_dropout_prob
|
37 |
+
self.attention_probs_dropout_prob = attention_probs_dropout_prob
|
38 |
+
self.max_position_embeddings = max_position_embeddings
|
39 |
+
self.type_vocab_size = type_vocab_size
|
40 |
+
self.initializer_range = initializer_range
|
41 |
+
self.layer_norm_eps = layer_norm_eps
|
42 |
+
self.position_embedding_type = position_embedding_type
|
43 |
+
self.use_cache = use_cache
|
44 |
+
self.classifier_dropout = classifier_dropout
|
45 |
+
self.linear_layer = linear_layer
|
46 |
+
self.linear_layer_output = linear_layer_output
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "RewardModel/RewardModelTokenizer",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "BertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|