Qinyu Luo

作者您好～ 我看到目前支持的模型有chatglm-6b-int4-qe，chatglm-6b-int4，chatglm-6b，chatyuan。请问是否支持基于chatGLM finetune后的模型呢（ptuning或者lora）? 我在加载自己本地finetune后的checkpoint的时候，遇到如下警告，模型没有加载成功。 Some weights of ChatGLMForConditionalGeneration were not initialized from the model checkpoint at (我的路径）/ChatGLM-6B/ptuning/output/adgen-chatglm-6b-pt-2048-2e-2/checkpoint-3000 and are newly initialized: ['transformer.layers.5.mlp.dense_4h_to_h.bias', 'transformer.layers.13.mlp.dense_4h_to_h.bias', 'transformer.layers.21.attention.dense.weight', 'transformer.layers.3.mlp.dense_4h_to_h.bias', 'transformer.layers.17.mlp.dense_h_to_4h.weight', 'transformer.layers.19.attention.dense.bias', 'transformer.layers.6.mlp.dense_h_to_4h.weight', 'transformer.layers.18.input_layernorm.bias', 'transformer.layers.22.input_layernorm.weight',...

仅仅提供了由RepoAgent生成的详尽的代码文档，这里没有做任何代码修改。 RepoAgent项目地址： https://github.com/OpenBMB/RepoAgent 论文地址：http://arxiv.org/abs/2402.16667

Can I use ReFL method to train another dataset for a new reward model?

1

Hi, thanks for your fantastic work! I am trying to understand how to use the ReFL method to train a new reward model with a custom dataset. Specifically, I am...

I would like to have a try on NextGPT, but it seems that the online demo doesn't work right now.  could you please fix it? Thank you!

Error when running the interactive_shell

1

--------------------------------------------------------------------------- ModuleNotFoundError Traceback (most recent call last) Cell In[7], line 5 2 # change to any task_id in train, dev (not test to preserve test data sanctity). 3 # e.g.,...

Question and Performance comparison between models

4

Should I just paste and put your complete prompt into the system prompt for the model? I find that most of the time the model doesn't follow the structure. This...