Update README.md

README.md

@@ -13,7 +13,7 @@ language:
 ---
 
 
-# GreenLLaMA-7B
+# DetoxLLM-7B
 
 <p align="center">
     <br>
@@ -23,9 +23,9 @@ language:
 
 </p>
 
-This model card corresponds to the GreenLLaMA-7B detoxification model based on [LLaMA-2](https://huggingface.co/meta-llama/Llama-2-7b). The model is finetuned with Chain-of-Thought (CoT) explanation.
+This model card corresponds to the DetoxLLM-7B detoxification model based on [LLaMA-2](https://huggingface.co/meta-llama/Llama-2-7b). The model is finetuned with Chain-of-Thought (CoT) explanation.
 
-**Paper**: [GreenLLaMA: A Framework for Detoxification with Explanations](https://arxiv.org/abs/2402.15951)
+**Paper**: [GreenLLaMA: A Framework for Detoxification with Explanations](https://arxiv.org/abs/2402.15951) **(EMNLP 2024 Main)**
 
 **Authors**: Md Tawkat Islam Khondaker, Muhammad Abdul-Mageed, Laks V.S. Lakshmanan
 
@@ -35,7 +35,7 @@ Summary description and brief definition of inputs and outputs.
 
 ### Description
 
-GreenLLaMA is the first comprehensive end-to-end detoxification framework trained on cross-platform pseudo-parallel corpus. GreenLLaMA further introduces explanation to promote transparency and trustworthiness. The framework also demonstrates robustness against adversarial toxicity.
+DetoxLLM is the first comprehensive end-to-end detoxification framework trained on cross-platform pseudo-parallel corpus. DetoxLLM further introduces explanation to promote transparency and trustworthiness. The framework also demonstrates robustness against adversarial toxicity.
 
 ### Usage
 
@@ -48,7 +48,7 @@ Below we share some code snippets on how to get quickly started with running the
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-model_name = "UBC-NLP/GreenLLaMA-7b"
+model_name = "UBC-NLP/DetoxLLM-7B"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
@@ -71,7 +71,7 @@ print(tokenizer.decode(outputs[0]))
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-model_name = "UBC-NLP/GreenLLaMA-7b"
+model_name = "UBC-NLP/DetoxLLM-7B"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
@@ -97,7 +97,7 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-model_name = "UBC-NLP/GreenLLaMA-7b"
+model_name = "UBC-NLP/DetoxLLM-7B"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
@@ -118,7 +118,7 @@ print(tokenizer.decode(outputs[0]))
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-model_name = "UBC-NLP/GreenLLaMA-7b"
+model_name = "UBC-NLP/DetoxLLM-7B"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.bfloat16)
@@ -143,7 +143,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
 quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 
-model_name = "UBC-NLP/GreenLLaMA-7b"
+model_name = "UBC-NLP/DetoxLLM-7B"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=quantization_config)
@@ -166,7 +166,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
 quantization_config = BitsAndBytesConfig(load_in_4bit=True)
 
-model_name = "UBC-NLP/GreenLLaMA-7b"
+model_name = "UBC-NLP/DetoxLLM-7B"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=quantization_config)
@@ -194,7 +194,7 @@ These models have certain limitations that users should be aware of.
 
 ### Intended Usage
 
-The intended use of GreenLLaMA is for the detoxification tasks. We aim to help researchers to build an end-to-end complete detoxification framework. GreenLLaMA can also be regarded as a promising baseline to develop more robust and effective detoxification frameworks.
+The intended use of DetoxLLM is for the detoxification tasks. We aim to help researchers to build an end-to-end complete detoxification framework. DetoxLLM can also be regarded as a promising baseline to develop more robust and effective detoxification frameworks.
 
 
 ### Limitations
@@ -202,9 +202,9 @@ The intended use of GreenLLaMA is for the detoxification tasks. We aim to help r
 * **Data Generation Process:**
   This work uses ChatGPT, a gpt-3.5-turbo version from June, 2023. Since the model can be updated on a regular interval, the data generation process should be treated accordingly.
 * **Data Quality:**
-  GreenLLaMA proposes an automated data generation pipeline to create a pseudo-parallel cross-platform corpus. The synthetic data generation process involves multi-stage data processing without the necessity of direct human inspection. Although this automated pipeline makes the overall data generation process scalable, it comes at the risk of allowing low-quality data in our cross-platform corpus. Hence, human inspection is recommended to remove any sort of potential vulnerability and maintain a standard quality of the corpus.
+  DetoxLLM proposes an automated data generation pipeline to create a pseudo-parallel cross-platform corpus. The synthetic data generation process involves multi-stage data processing without the necessity of direct human inspection. Although this automated pipeline makes the overall data generation process scalable, it comes at the risk of allowing low-quality data in our cross-platform corpus. Hence, human inspection is recommended to remove any sort of potential vulnerability and maintain a standard quality of the corpus.
 * **Model Responses:** 
-  Although GreenLLaMA exhibits impressive ability in generating detoxified responses, we believe there is still room for improvement for the model in terms of producing meaning-preserved detoxified outcomes. Moreover, the models can sometimes be vulnerable to implicit, adversarial tokens and continue to produce toxic content. Therefore, we recommend that GreenLLaMA should be couched with caution before deployment. 
+  Although DetoxLLM exhibits impressive ability in generating detoxified responses, we believe there is still room for improvement for the model in terms of producing meaning-preserved detoxified outcomes. Moreover, the models can sometimes be vulnerable to implicit, adversarial tokens and continue to produce toxic content. Therefore, we recommend that DetoxLLM should be couched with caution before deployment. 
 
 ### Ethical Considerations and Risks
 
@@ -214,13 +214,13 @@ In creating an open model, we have carefully considered the following:
 * **Data Collection and Release:** 
   We compile datasets from a wide range of platforms. To ensure proper credit assignment, we refer users to the original publications in our paper. We create the cross-platform detoxification corpus for academic research purposes. We intend to share the corpus in the future. We would also like to mention that some content are generated using GPT-4 for illustration purposes.
 * **Potential Misuse and Bias:**
-  GreenLLaMA can potentially be misused to generate toxic and biased content. For these reasons, we recommend that GreenLLaMA not be used in applications without careful prior consideration of potential misuse and bias.
+  GreenLLaMA can potentially be misused to generate toxic and biased content. For these reasons, we recommend that DetoxLLM not be used in applications without careful prior consideration of potential misuse and bias.
 
 ## Citation
 If you use GreenLLaMA for your scientific publication, or if you find the resources in this repository useful, please cite our paper as follows:
 ```
-@inproceedings{Khondaker2024GreenLLaMA,
-  title={GreenLLaMA: A Framework for Detoxification with Explanations},
+@inproceedings{Khondaker2024DetoxLLM,
+  title={DetoxLLM: A Framework for Detoxification with Explanations},
   author={Md. Tawkat Islam Khondaker and Muhammad Abdul-Mageed and Laks V. S. Lakshmanan},
   year={2024},
   url={https://arxiv.org/abs/2402.15951}