Leekinxun
Leekinxun
### Class | 类型 函数插件 ### Feature Request | 功能请求 希望用国产大模型,例如:文心、智谱、星火,通过api调用接入autogen
When I localize deployment, the log shows "Application startup complete", but when I open the page, it shows "An error has occurred while fetching types". How can I solve this...
### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction 训练脚本如下: CUDA_VISIBLE_DEVICES=1,2,3 python src/train.py \ --deepspeed deepspeed/ds_config_zero3.json\ --stage sft \ --do_train \ --model_name_or_path "/data02/pretrained_models/Qwen1.5-4B-Chat"...
### Describe the Question Please provide a clear and concise description of what the question is. chatglm2是不是做不了PPO相关的训练,我在rm模型中用了bert训练,但是无法合并参数,同时第四部的rl训练也显示ChatGLM2模型没有AutoModelForCausalLMWithValueHead,请问这种情况是不是只能换模型了
如题,如何自定义添加其他闭源模型的API,类似已有的ZHIPUAI那样,应该更改添加哪些步骤的代码,感谢!