Update README.md

README.md

@@ -4,11 +4,15 @@ language:
 - ja
 ---
 
-量子化時に日本語と中国語を多めに使っているため、[hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4](https://huggingface.co/hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4)より日本語データを使って計測したPerplexityが良い事がわかっています  
-Because Japanese and Chinese are used a lot during quantization, It is known that Perplexity measured using Japanese data is better than [hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4](https://huggingface.co/hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4).  
 
-![kaizoku](kaizoku.png)
+llama3.1-8bのAWQ量子化版です。  
+4GB超のGPUメモリがあれば高速に動かす事ができます。  
+
+This is the AWQ quantization version of llama3.1-8b.  
+If you have more than 4GB of GPU memory, you can run it at high speed.　　
 
+量子化時に日本語と中国語を多めに使っているため、[hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4](https://huggingface.co/hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4)より日本語データを使って計測したPerplexityが良い事がわかっています  
+Because Japanese and Chinese are used a lot during quantization, It is known that Perplexity measured using Japanese data is better than [hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4](https://huggingface.co/hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4).  
 
 
 ```
@@ -48,5 +52,6 @@ inputs = tokenizer.apply_chat_template(
 outputs = model.generate(**inputs, do_sample=True, max_new_tokens=256)
 print(tokenizer.batch_decode(outputs[:, inputs['input_ids'].shape[1]:], skip_special_tokens=True)[0])
 
+```
 
-```
+![kaizoku](kaizoku.png)