Update README.md

README.md

@@ -10,7 +10,7 @@ language:
 inference: false
 ---
 # Model Card for Mobius-12B-base-m1 
-The Mobius-12B-base-m1 Large Language Model (LLM) is a pretrained model based on RWKV v5 arch. We use 0.01B tokens to post train this model.
+The Mobius-12B-base-m1 Large Language Model (LLM) is a pretrained model based on RWKV v5 arch. We use 0.01B tokens to post train this model for alignment benchmarks.
 
 
 ## Warning
@@ -27,6 +27,9 @@ User: {Instruction|prompt}\n\nAssistant:
 ```
 
 ## Run the model
+
+[need to convert checkpoint to HF format](https://github.com/xiaol/RWKV-World-HF-Tokenizer?tab=readme-ov-file#huggingface-rwkv-world-model-convert)
+
 Need to install this [PR](https://github.com/huggingface/transformers/pull/26963)
 pip install -e git://github.com/BBuf/transformers.git