Update README.md

README.md

@@ -5,12 +5,12 @@ license: cc-by-nc-4.0
 # ICKG Model Card
 
 ## Model Details
-ICKG (Integrated Contextual Knowledge Graph Generator) is a knowledge graph construction (KGC) task-specific instruction-following language model fine-tuned from LMSYS's Vicuna-7B, which itself is derived from Meta's LLaMA LLM. 
+ICKG (Integrated Contextual Knowledge Graph Generator) 2.0 is a knowledge graph construction (KGC) task-specific instruction-following language model fine-tuned from LMSYS's Vicuna-7B, which itself is derived from Meta's LLaMA LLM. 
 
 - **Developed by**: [Xiaohui Li](https://xiaohui-victor-li.github.io/)
 - **Model type**: Auto-regressive language model based on the transformer architecture.
 - **License**: Non-commercial
-- **Finetuned from model**: [Vicuna-7B](https://huggingface.co/lmsys/vicuna-7b-v1.3) (originally from [LLaMA](https://arxiv.org/abs/2302.13971)).
+- **Finetuned from model**: [Vicuna-7B](https://huggingface.co/lmsys/vicuna-7b-v1.5) (originally from [LLaMA 2.0](https://ai.meta.com/llama/)).
 
 ## Model Sources
 - **Repository**: [https://github.com/your-github-repo](https://github.com/your-github-repo)
@@ -18,14 +18,14 @@ ICKG (Integrated Contextual Knowledge Graph Generator) is a knowledge graph cons
 - **Paper**: [https://arxiv.org/abs/your-paper-id](https://arxiv.org/abs/your-paper-id)
 
 ## Uses
-The primary use of iKG LLM is for generating knowledge graphs (KG) based on instruction-following capability with specialized prompts. It's intended for researchers, data scientists, and developers interested in natural language processing, and knowledge graph construction.
+The primary use of ICKG LLM is for generating knowledge graphs (KG) based on instruction-following capability with specialized prompts. It's intended for researchers, data scientists, and developers interested in natural language processing, and knowledge graph construction.
 
 ## How to Get Started with the Model
 - **Python Code**: [https://github.com/your-github-repo/tree/main#api](https://github.com/your-github-repo/tree/main#api)
 - **Command line interface of FastChat**: [https://github.com/your-github-repo#ikg-weights](https://github.com/your-github-repo#ikg-weights)
 
 ## Training Details
-iKG is fine-tuned from Vicuna-7B using ~3K instruction-following demonstrations including KG construction input document and extracted KG triplets as response output. iKG is thus learnt to extract list of KG triplets from given text document via prompt engineering. For more in-depth training details, refer to the "Generative Knowledge Graph Construction with Fine-tuned LLM" section of [the accompanying paper](https://arxiv.org/abs/your-paper-id).
+ICKG 2.0 is fine-tuned from the latest Vicuna-7B using ~3K instruction-following demonstrations including KG construction input document and extracted KG triplets as response output. iKG is thus learnt to extract list of KG triplets from given text document via prompt engineering. For more in-depth training details, refer to the "Generative Knowledge Graph Construction with Fine-tuned LLM" section of [the accompanying paper](https://arxiv.org/abs/your-paper-id).
 
 - **Prompt Template**: The entities and relationship can be customized for specific tasks. `<input_text>` is the document text to replace.
 
@@ -65,7 +65,7 @@ iKG is fine-tuned from Vicuna-7B using ~3K instruction-following demonstrations
   ```
 
 ## Evaluation
-iKG has undergone preliminary evaluation comparing its performance to GPT-3.5, GPT-4, and the original Vicuna-7B model. With respect to the KG construction task, it outperforms GPT-3.5 and Vicuna-7B while exhibiting comparative capability as GPT-4. iKG excels in generating instruction-based knowledge graphs with a particular emphasis on quality and adherence to format.
+ICKG has undergone preliminary evaluation comparing its performance to GPT-3.5, GPT-4, and the original Vicuna-7B model. With respect to the KG construction task, it outperforms GPT-3.5 and Vicuna-7B while exhibiting comparative capability as GPT-4. iKG excels in generating instruction-based knowledge graphs with a particular emphasis on quality and adherence to format.
 
 For a more detailed introduction, refer to [the accompanying paper](https://arxiv.org/abs/your-paper-id).