harshavardhan88858/deepseek-qwen-grpo-reasoning-v1
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: harshavardhan88858/deepseek-qwen-grpo-reasoning-v1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 06:52:47 +08:00
commit a503b24c06
12 changed files with 710 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
chat_template.jinja Normal file
View File

@@ -0,0 +1,10 @@
{% for message in messages %}
{% if message['role'] == 'system' %}
System: {{ message['content'] }}
{% elif message['role'] == 'user' %}
User: {{ message['content'] }}
{% elif message['role'] == 'assistant' %}
Assistant: {{ message['content'] }}
{% endif %}
{% endfor %}
Assistant: