Update README.md

README.md

@@ -9,17 +9,32 @@ metrics:
 pipeline_tag: text-classification
 ---
 
+
 **Dataset Card for LifeTox**
 
 As large language models become increasingly integrated into daily life, detecting implicit toxicity across diverse contexts is crucial. To this end, we introduce *LifeTox*, a dataset designed for identifying implicit toxicity within a broad range of advice-seeking scenarios. Unlike existing safety datasets, *LifeTox* comprises diverse contexts derived from personal experiences through open-ended questions. Our experiments demonstrate that RoBERTa fine-tuned on *LifeTox* matches or surpasses the zero-shot performance of large language models in toxicity classification tasks. These results underscore the efficacy of *LifeTox* in addressing the complex challenges inherent in implicit toxicity.
 
 **LifeTox Moderator 13B**
 
-LifeTox Moderator 13B is based on [Llama-2-13b-chat-hf](meta-llama/Llama-2-13b-chat-hf). We fine-tuned this pre-trained model on LifeTox [dataset](https://huggingface.co/datasets/mbkim/LifeTox). To use our model as a generalized moderator or specific pipelines, please refer to the paper ['LifeTox: Unveiling Implicit Toxicity in Life advice'](https://arxiv.org/abs/2311.09585). LifeTox Moderator 13B is trained as a toxicity classifier as
+LifeTox Moderator 13B is based on [Llama-2-13b-chat-hf](meta-llama/Llama-2-13b-chat-hf). We fine-tuned this pre-trained model on LifeTox [dataset](https://huggingface.co/datasets/mbkim/LifeTox) with LoRa. To use our model as a generalized moderator or specific pipelines, please refer to the paper ['LifeTox: Unveiling Implicit Toxicity in Life advice'](https://arxiv.org/abs/2311.09585). LifeTox Moderator 13B is trained as a toxicity classifier as
 ```
 Input: "[INST] Evaluate the toxicity of answer for given questions. You should only label as 'Unsafe' or 'Safe' [/INST]\n" + "Question: " +  item['query'] + "\nAnswer: " + item[‘response’] + "\nLabel"
 Output: GT_Label (Safe or Unsafe)
 ```
+Please initialize this model as
+```
+peft_config = LoraConfig(
+            lora_alpha=16,
+            lora_dropout=0.1,
+            target_modules=["q_proj", "v_proj", "k_proj", "o_proj"],
+            r=64,
+            bias="none",
+            task_type="CAUSAL_LM"
+        )
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+model = AutoPeftModelForCausalLM.from_pretrained(model_path, config=peft_config, device_map="auto")
+```
 
 ### LifeTox Sources