diff --git a/README.md b/README.md
index c6482091..d2105e8b 100644
--- a/README.md
+++ b/README.md
@@ -34,7 +34,7 @@
       
 ## News
 - [x] [2024.1.17] [LongLoRA](https://arxiv.org/abs/2309.12307) has been accepted by **ICLR 2024** as an **Oral** presentation.
-- [x] [2023.11.19] We release a new version of LongAlpaca models, [LongAlpaca-7B-16k](https://huggingface.co/Yukang/LongAlpaca-7B-16k), [LongAlpaca-7B-16k](https://huggingface.co/Yukang/LongAlpaca-13B-16k), and [LongAlpaca-7B-16k](https://huggingface.co/Yukang/LongAlpaca-70B-16k). These models are fine-tuned on a subset LongAlpaca-12k dataset with LongLoRA in SFT, [LongAlpaca-16k-length](https://huggingface.co/datasets/Yukang/LongAlpaca-16k-length). We evaluate the [LongAlpaca-7B-16k](https://huggingface.co/Yukang/LongAlpaca-7B-16k) model on LongBench and L-Eval benchmarks and results can be found [here](https://github.com/dvlab-research/LongLoRA/tree/main/benchmarks).
+- [x] [2023.11.19] We release a new version of LongAlpaca models, [LongAlpaca-7B-16k](https://huggingface.co/Yukang/LongAlpaca-7B-16k), [LongAlpaca-13B-16k](https://huggingface.co/Yukang/LongAlpaca-13B-16k), and [LongAlpaca-70B-16k](https://huggingface.co/Yukang/LongAlpaca-70B-16k). These models are fine-tuned on a subset LongAlpaca-12k dataset with LongLoRA in SFT, [LongAlpaca-16k-length](https://huggingface.co/datasets/Yukang/LongAlpaca-16k-length). We evaluate the [LongAlpaca-7B-16k](https://huggingface.co/Yukang/LongAlpaca-7B-16k) model on LongBench and L-Eval benchmarks and results can be found [here](https://github.com/dvlab-research/LongLoRA/tree/main/benchmarks).
 - [x] [2023.11.2] We have updated our LongAlpaca models from alpaca prompting to llama2 prompting, which is consistent to their pre-trained models. Please refer to the [inference code](https://github.com/dvlab-research/LongLoRA/blob/2345c6d030f61ac3a031906386a103a5b05e0e6f/inference.py#L18) with the llama2 prompting.
 - [x] [2023.10.23] We support the combination of [QLoRA](https://github.com/artidoro/qlora) and LongLoRA in the [supervised fine-tuning](supervised-fine-tune-qlora.py), for further reduction of the GPU memory cost. We release the LoRA weights of a 7B model at [LongAlpaca-7B-qlora-weights](https://huggingface.co/Yukang/LongAlpaca-7B-qlora-weights).
 - [x] [2023.10.18] We support [StreamingLLM](https://github.com/mit-han-lab/streaming-llm) inference on our LongAlpaca models. This increases the context-length of the multi-round dialogue in StreamingLLM.