Upload 11 files

LICENSE

@@ -0,0 +1,190 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright Nicholas Kluge Corrêa
+
+   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.

README.md

@@ -1,3 +1,71 @@
----
-license: apache-2.0
----
+# RewardModel (Portuguese-BR)
+
+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.
+
+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.
+
+The model was trained with a dataset composed of `prompt`, `completions`, and annotated `rewards`.
+
+> Note: These prompt + completions are samples of intruction datasets created via the [Self-Instruct](https://github.com/yizhongw/self-instruct) framework.
+
+## Usage
+
+Here's an example of how to use the `RewardModelPT` to score the quality of a response to a given prompt:
+
+```python
+from transformers import AutoTokenizer,AutoConfig, AutoModel
+import torch
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+config = AutoConfig.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, revision='main') 
+tokenizer = AutoTokenizer.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, config=config, revision='main')
+rewardModel = AutoModel.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, config=config, revision='main') 
+
+rewardModel.to(device)
+rewardModel.eval()
+
+
+# Define the question and response
+question = "What is the capital of France?"
+response1 = "Paris, France's capital, is a major European city and a global center for art, fashion, gastronomy and culture."
+response2 = "Google it pal."
+
+# Tokenize the question and response
+tokens = tokenizer(question, response1,
+                return_token_type_ids=False,
+                return_tensors="pt", 
+                return_attention_mask=True)
+
+tokens.to(device)
+
+# Score the response
+score = model(**tokens, alpha=10).item()
+
+print(f"Question: {question} \n")
+print(f"Response 1: {response1} Score: {score:.3f}")
+
+tokens = tokenizer(question, response2,
+                return_token_type_ids=False,
+                return_tensors="pt", 
+                return_attention_mask=True)
+
+tokens.to(device)
+
+score = model(**tokens, alpha=10).item()
+
+print(f"Response 2: {response2} Score: {score:.3f}")
+```
+
+This will output the following:
+
+```markdown
+>>> Question: What is the capital of France? 
+
+>>>Response: Paris, France's capital, is a major European city and a global center for art, fashion, gastronomy and culture. Score: 3.183
+>>>Response: Google it pal. Score: -5.781
+```
+
+## License
+
+The `RewardModelPT` is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.

RewardModel_emissions.csv

@@ -0,0 +1,2 @@
+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
+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

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "RewardModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "reward_model_config.RewardModelConfig",
+    "AutoModel": "reward_model.RewardModel"
+  },
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "linear_layer": 128,
+  "linear_layer_output": 1,
+  "max_position_embeddings": 512,
+  "model_type": "bert-reward",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea3a11bda31a8c8112131c41c7480284f254d1599c3a2a0880dba044da7821df
+size 433770725

reward_model.py

@@ -0,0 +1,44 @@
+from transformers import BertPreTrainedModel, BertModel, BertConfig
+from .reward_model_config import RewardModelConfig
+import torch
+
+class RewardModel(BertPreTrainedModel):
+    """
+    RewardModel class for PyTorch
+
+    Args:
+        config (transformers.configuration): model configuration
+
+    Returns:
+        output (torch.tensor): tensor containing the output logits [-1,1]
+    """
+    config_class = RewardModelConfig
+
+    def __init__(self, config):
+        super().__init__(config)
+        self.bert = BertModel(config)
+        
+        self.cls_layer1 = torch.nn.Linear(config.hidden_size,config.linear_layer)
+        self.relu1 = torch.nn.ReLU()
+        self.ff1 = torch.nn.Linear(config.linear_layer,config.linear_layer)
+        self.tanh1 = torch.nn.Tanh()
+        self.ff2 = torch.nn.Linear(config.linear_layer,config.linear_layer_output)
+
+    def forward(self, input_ids, attention_mask, alpha=1):
+        
+        outputs = self.bert(input_ids=input_ids, attention_mask=attention_mask)
+        
+        logits = outputs.last_hidden_state[:,0,:]
+        output = self.cls_layer1(logits)
+        output = self.relu1(output)
+        output = self.ff1(output)
+        output = self.tanh1(output)
+        output = self.ff2(output)
+
+        # Apply alpha and beta to output (if not training)  
+        if not self.training:
+            
+            # alpha multiplies the output by a scalar
+            output = torch.mul(output, alpha)
+
+        return output

reward_model_config.py

@@ -0,0 +1,46 @@
+from transformers import PretrainedConfig
+
+class RewardModelConfig(PretrainedConfig):
+    model_type="bert-reward"
+
+    def __init__(
+        self,
+        vocab_size=28996,
+        hidden_size=768,
+        num_hidden_layers=12,
+        num_attention_heads=12,
+        intermediate_size=3072,
+        hidden_act="gelu",
+        hidden_dropout_prob=0.1,
+        attention_probs_dropout_prob=0.1,
+        max_position_embeddings=512,
+        type_vocab_size=2,
+        initializer_range=0.02,
+        layer_norm_eps=1e-12,
+        pad_token_id=0,
+        position_embedding_type="absolute",
+        use_cache=True,
+        classifier_dropout=None,
+        linear_layer=128,
+        linear_layer_output=1,
+        **kwargs,
+    ):
+        super().__init__(pad_token_id=pad_token_id, **kwargs)
+
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.hidden_act = hidden_act
+        self.intermediate_size = intermediate_size
+        self.hidden_dropout_prob = hidden_dropout_prob
+        self.attention_probs_dropout_prob = attention_probs_dropout_prob
+        self.max_position_embeddings = max_position_embeddings
+        self.type_vocab_size = type_vocab_size
+        self.initializer_range = initializer_range
+        self.layer_norm_eps = layer_norm_eps
+        self.position_embedding_type = position_embedding_type
+        self.use_cache = use_cache
+        self.classifier_dropout = classifier_dropout
+        self.linear_layer = linear_layer
+        self.linear_layer_output = linear_layer_output

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "RewardModel/RewardModelTokenizer",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}