Update README.md

README.md

@@ -16,7 +16,7 @@ Our B2NER models, trained on B2NERD, outperform GPT-4 by 6.8-12.0 F1 points and
  - 📖 Paper: [Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition](http://arxiv.org/abs/2406.11192)
  - 🎮 Github Repo: https://github.com/UmeanNever/B2NER
  - 📀 Data: See below data section. You can download from [HuggingFace](https://huggingface.co/datasets/Umean/B2NERD) or [Google Drive](https://drive.google.com/file/d/11Wt4RU48i06OruRca2q_MsgpylzNDdjN/view?usp=drive_link).
- - 💾 Model (LoRA Adapters): Current repo saves the B2NER model LoRA adapter based on InternLM2.5-7B.
+ - 💾 Model (LoRA Adapters): Current repo saves the B2NER model LoRA adapter based on InternLM2.5-7B. See [20B model](https://huggingface.co/Umean/B2NER-Internlm2-20B-LoRA) for a 20B adapter.
 
 **See github repo for more information about model usage and this work.**