SungJoo commited on
Commit
9c04e2c
1 Parent(s): a41b016

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +73 -169
README.md CHANGED
@@ -1,199 +1,103 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
 
 
 
 
 
 
 
 
 
 
4
  ---
5
 
6
- # Model Card for Model ID
7
-
8
- <!-- Provide a quick summary of what the model is/does. -->
9
-
10
 
 
11
 
12
  ## Model Details
13
 
14
  ### Model Description
15
 
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
 
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
 
28
- ### Model Sources [optional]
29
 
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
 
36
  ## Uses
37
 
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
- ### Direct Use
41
-
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
 
58
  ## Bias, Risks, and Limitations
59
 
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
 
70
  ## How to Get Started with the Model
71
 
72
- Use the code below to get started with the model.
73
 
74
- [More Information Needed]
 
 
 
 
 
75
 
76
  ## Training Details
77
 
78
  ### Training Data
79
-
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
-
82
- [More Information Needed]
83
 
84
  ### Training Procedure
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
 
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
-
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
-
153
- ## Technical Specifications [optional]
154
-
155
- ### Model Architecture and Objective
156
-
157
- [More Information Needed]
158
-
159
- ### Compute Infrastructure
160
-
161
- [More Information Needed]
162
-
163
- #### Hardware
164
-
165
- [More Information Needed]
166
-
167
- #### Software
168
-
169
- [More Information Needed]
170
-
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
-
175
- **BibTeX:**
176
-
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
184
-
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
-
187
- [More Information Needed]
188
-
189
- ## More Information [optional]
190
-
191
- [More Information Needed]
192
-
193
- ## Model Card Authors [optional]
194
-
195
- [More Information Needed]
196
-
197
- ## Model Card Contact
198
-
199
- [More Information Needed]
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
+ language:
5
+ - en
6
+ tags:
7
+ - causal-lm
8
+ - Large Language Model
9
+ - LLM
10
+ - detoxification
11
+ - unbias
12
+ - bias
13
+ - instruction
14
+ - finetuned
15
+ - llama2
16
  ---
17
 
18
+ # Model Card for SungJoo/llama2-7b-sft-detox
 
 
 
19
 
20
+ This model is an instruction-tuned version of meta-llama/Llama-2-7b-hf, fine-tuned to reduce toxicity in Large Language Models (LLMs).
21
 
22
  ## Model Details
23
 
24
  ### Model Description
25
 
26
+ This is an instruction-tuned model based on the LLaMA-2-7b architecture. It has been fine-tuned using a comprehensive instruction dataset specifically designed for detoxification of LLMs.
 
 
27
 
28
+ - **Developed by:** Sungjoo Byun (Grace Byun)
29
+ - **Model type:** Auto-regressive language model
30
+ - **Language(s) (NLP):** English
31
+ - **License:** Apache License 2.0
32
+ - **Finetuned from:** meta-llama/Llama-2-7b-hf
 
 
33
 
34
+ ### Model Sources
35
 
36
+ - **Repository:** TBD
37
+ - **Paper:** TBD
 
 
 
38
 
39
  ## Uses
40
 
41
+ This model is intended to be used for generating less toxic language in various applications, including chatbots and other NLP systems.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
 
43
  ## Bias, Risks, and Limitations
44
 
45
+ While this model aims to reduce toxicity, it may still generate biased or harmful content. Users should apply this model with caution and review outputs for sensitive applications.
 
 
 
 
 
 
 
 
46
 
47
  ## How to Get Started with the Model
48
 
49
+ Use the code below to get started with the model:
50
 
51
+ ```python
52
+ from transformers import AutoTokenizer, AutoModelForCausalLM
53
+
54
+ tokenizer = AutoTokenizer.from_pretrained("SungJoo/llama2-7b-sft-detox")
55
+ model = AutoModelForCausalLM.from_pretrained("SungJoo/llama2-7b-sft-detox")
56
+ ```
57
 
58
  ## Training Details
59
 
60
  ### Training Data
61
+ The model was fine-tuned using a dataset specifically created to detoxify LLMs. This dataset will be publicly available soon.
 
 
 
62
 
63
  ### Training Procedure
64
+ The model was trained using full fine-tuning with the following hyperparameters:
65
+
66
+ | **Hyperparameter** | **Value** |
67
+ |--------------------|-----------|
68
+ | Batch size | 128 |
69
+ | Learning rate | 2e-5 |
70
+ | Epochs | 3 |
71
+ | Max length | 512 |
72
+ | Weight decay | 0 |
73
+
74
+
75
+ The training was conducted on 4 A100 80GB GPUs.
76
+
77
+ ## Objective
78
+ The main objective of this research is to reduce toxicity in LLMs by applying instruction tuning and Direct Preference Optimization (DPO).
79
+ This version has been tuned with instruction tuning only.
80
+ A comprehensive instruction and DPO dataset was constructed for this purpose, which will be released in the future.
81
+
82
+ | **Model** | **LLaMA-2-base** | | **Finetuned LLaMA-2** | | **DPO LLaMA-2** | |
83
+ |--------------------|-------------------|-----------------------|-----------------------|-------------------------|-----------------------|-------------------------|
84
+ | **Category** | **\>=0.5 (%)** | **Count** | **\>=0.5 (%)** | **Count** | **\>=0.5 (%)** | **Count** |
85
+ | **TOXICITY** | 4.46 | 4,438 | 3.61 | 3,593 | 2.39 | 2,377 |
86
+ | | | | <span style="color:blue;">(-0.85)</span> | <span style="color:blue;">(-845)</span> | <span style="color:green;">(-1.22)</span> | <span style="color:green;">(-1,216)</span> |
87
+ | **SEVERE_TOXICITY**| 0.08 | 77 | 0.07 | 70 | 0.03 | 31 |
88
+ | | | | <span style="color:blue;">(-0.01)</span> | <span style="color:blue;">(-7)</span> | <span style="color:green;">(-0.04)</span> | <span style="color:green;">(-39)</span> |
89
+ | **IDENTITY_ATTACK**| 0.79 | 788 | 0.42 | 413 | 0.28 | 274 |
90
+ | | | | <span style="color:blue;">(-0.37)</span> | <span style="color:blue;">(-375)</span> | <span style="color:green;">(-0.14)</span> | <span style="color:green;">(-139)</span> |
91
+ | **INSULT** | 1.97 | 1,961 | 1.60 | 1,588 | 0.90 | 892 |
92
+ | | | | <span style="color:blue;">(-0.37)</span> | <span style="color:blue;">(-373)</span> | <span style="color:green;">(-0.70)</span> | <span style="color:green;">(-696)</span> |
93
+ | **PROFANITY** | 2.10 | 2,086 | 1.76 | 1,753 | 1.04 | 1,030 |
94
+ | | | | <span style="color:blue;">(-0.34)</span> | <span style="color:blue;">(-333)</span> | <span style="color:green;">(-0.72)</span> | <span style="color:green;">(-723)</span> |
95
+ | **THREAT** | 1.43 | 1,424 | 0.92 | 919 | 0.76 | 754 |
96
+ | | | | <span style="color:blue;">(-0.51)</span> | <span style="color:blue;">(-505)</span> | <span style="color:green;">(-0.16)</span> | <span style="color:green;">(-165)</span> |
97
+ *Comparison of LLaMA-2-base, Finetuned LLaMA-2, and DPO LLaMA-2 across various categories. Reductions in blue indicate comparisons between the base model and the fine-tuned model, while text in green represents comparisons between the fine-tuned model and the DPO model.*
98
+
99
+ The table above shows the effectiveness of this model in reducing bias, measured using the RealToxicityPrompt dataset and the Perspective API.
100
+
101
+ ## Contact
102
+ For any questions or issues, please contact byunsj@snu.ac.kr.
103