fix vicuna template

README.md

@@ -68,8 +68,8 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/6ba60acc-e2e2-4bec-b846
 > **Default module** is used for the `--lora_target` argument, you can use `--lora_target all` to specify all the available modules.
 >
 > For the "base" models, the `--template` argument can be chosen from `default`, `alpaca`, `vicuna` etc. But make sure to use the **corresponding template** for the "chat" models.
->
-> Please refer to [template.py](src/llmtuner/extras/template.py) for a full list of models we supported.
+
+Please refer to [template.py](src/llmtuner/extras/template.py) for a full list of models we supported.
 
 ## Supported Training Approaches
 

README_zh.md

@@ -68,8 +68,8 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/6ba60acc-e2e2-4bec-b846
 > **默认模块**应作为 `--lora_target` 参数的默认值，可使用 `--lora_target all` 参数指定全部模块。
 >
 > 对于所有“基座”（Base）模型，`--template` 参数可以是 `default`, `alpaca`, `vicuna` 等任意值。但“对话”（Chat）模型请务必使用**对应的模板**。
->
-> 项目所支持模型的完整列表请参阅 [template.py](src/llmtuner/extras/template.py)。
+
+项目所支持模型的完整列表请参阅 [template.py](src/llmtuner/extras/template.py)。
 
 ## 训练方法
 

src/llmtuner/extras/template.py

@@ -336,7 +336,7 @@ def get_template_and_fix_tokenizer(
         "{{system}}"
     ],
     prompt=[
-        "USER: {{query}} ASSISTANT: "
+        "USER: {{query}} ASSISTANT:"
     ],
     system=(
         "A chat between a curious user and an artificial intelligence assistant. "
@@ -366,6 +366,7 @@ def get_template_and_fix_tokenizer(
 
 r"""
 Supports: https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1
+          https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1.1
           https://huggingface.co/IDEA-CCNL/Ziya2-13B-Chat
 """
 register_template(
@@ -397,7 +398,7 @@ def get_template_and_fix_tokenizer(
         "{{system}}"
     ],
     prompt=[
-        "Human: {{query}}###Assistant: "
+        "Human: {{query}}###Assistant:"
     ],
     system=(
         "A chat between a curious human and an artificial intelligence assistant. "