Update README.md

README.md

@@ -10,10 +10,13 @@ library_name: transformers
 ---
 # **NanoTranslator-L**
 
+English | [简体中文](README_zh-CN.md)
+
 ## Introduction
 
-这是 NanoTranslator 的 Large 型号，目前仅支持**英译中**。仓库中同时提供了 ONNX 版本的模型。
+This is the Large model of the NanoTranslator, currently supported only in **English to Chinese**.
 
+The ONNX version of the model is also available in the repository.
 
 
 | Size | Params. |  V.  |  H.  |  I.  |  L.  | Att. H. | KV H. | Tie Emb. |
@@ -35,7 +38,7 @@ library_name: transformers
 
 ## How to use
 
-Prompt 格式如下：
+Prompt format as follows：
 
 ```
 <|im_start|> {English Text} <|endoftext|>
@@ -84,7 +87,7 @@ print(response)
 
 It has been measured that reasoning with ONNX models will be **2-10 times faster** than reasoning directly with transformers models.
 
-You should switch to onnx branch manually and download to local.
+You should switch to [onnx branch](https://huggingface.co/Mxode/NanoTranslator-L/tree/onnx) manually and download to local.
 
 reference docs:
 
@@ -94,8 +97,6 @@ reference docs:
 **Using ORTModelForCausalLM**
 
 ```python
-# onnx branch: https://huggingface.co/Mxode/NanoTranslator-M/tree/onnx
-
 from optimum.onnxruntime import ORTModelForCausalLM
 from transformers import AutoTokenizer
 
@@ -122,4 +123,4 @@ text = "I love to watch my favorite TV series."
 
 response = pipe(text, max_new_tokens=64, do_sample=False)
 response
-```
+```