Update README.md

README.md

@@ -33,7 +33,7 @@ If you want to run it in a CPU-only environment, you may want to check this.
 
 ### Japanese automated benchmark result
 
-Benchmark settings are the same as (weblab-10b-instruction-sft-GPTQ)[https://huggingface.co/dahara1/weblab-10b-instruction-sft-GPTQ]  
+Benchmark settings are the same as [weblab-10b-instruction-sft-GPTQ](https://huggingface.co/dahara1/weblab-10b-instruction-sft-GPTQ)  
 
 |         Task         |Version| Metric |Value |   |Stderr|
 |----------------------|------:|--------|-----:|---|-----:|
@@ -90,9 +90,8 @@ output = model.generate(
         eos_token_id=tokenizer.eos_token_id)
 print(tokenizer.decode(output[0]))
 ```
-This is cherry picking result.  
-It is relatively easy to follow instructions for writing sentences.
 
+result.
 
 ```
 <s><s> [INST] <<SYS>>
@@ -133,6 +132,8 @@ So if you need high performance, please use the original model.
 
 ### 引用 Citations
 
+This model is based on the work of the following people:  
+
 ```tex
 @misc{elyzallama2023, 
       title={ELYZA-japanese-Llama-2-7b},