Update README.md

README.md

@@ -113,31 +113,17 @@ Use the code below to get started with the model.
 
 <!-- This section describes the evaluation protocols and provides the results. -->
 
-### Testing Data, Factors & Metrics
+We evaluated our model, JPharmatron-7B, with other general / domain-specific models of a similar size.
 
-#### Testing Data
+### Testing Data
 
 <!-- This should link to a Dataset Card if possible. -->
 
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
+[JPharmaBench](https://huggingface.co/collections/EQUES/jpharmabench-680a34acfe96870e41d050d8) and two existing benchmarks (JMMLU (pharma) and IgakuQA) were used.
 
 ### Results
 
-[More Information Needed]
-
-#### Summary
+Compared to Meditron3-Qwen2.5-7B and Llama3.1-Swallow-8B-Instruct-v0.3, JPharmatron-7B achieved the highest score on all of the five benchmarks.
 
 
 
@@ -170,8 +156,4 @@ See our preprint: [A Japanese Language Model and Three New Evaluation Benchmarks
 
 ## Model Card Authors [optional]
 
-@shinnosukeono
-
-## Model Card Contact
-
-[More Information Needed]
+[@shinnosukeono](https://shinnosukeono.github.io/)