Update README.md

README.md

@@ -26,14 +26,13 @@ JPharmatron-7B-base is a 7B large language model designed for pharmaceutical app
 
 <!-- Provide a longer summary of what this model is. -->
 
-The JPharmatron-7B-base is continually pre-trained using 10T tokens from Japanese and English datasets, based on Qwen2.5-7B.
+The JPharmatron-7B-base is continually pre-trained using 2B tokens from Japanese datasets, based on Qwen2.5-7B.
 
 - **Developed by:** EQUES Inc.
 - **Funded by [optional]:** [GENIAC Project](https://www.meti.go.jp/policy/mono_info_service/geniac/index.html)
 - **Model type:** Causal decoder-only
 - **Language(s) (NLP):** Japanese, English
 - **License:** CC-BY-SA-4.0
-- **Finetuned from model [optional]:** Qwen2.5-7B
 
 ### Model Sources [optional]