THUDM / VisualGLM-6B

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型
Apache License 2.0
4.1k stars 418 forks source link

可以直接用VisualGLM-6b进行reward model的训练吗? #26

Closed iamsile closed 1 year ago

iamsile commented 1 year ago

您好,想用VisualGLM-6b进行reward model的训练,目前输入数据是纯文本,自己照着deepspeed_chat改了一下,发现在计算时总出错,具体log如下: File "/opt/conda/envs/rlhf_tw_test/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/opt/conda/envs/rlhf_tw_test/lib/python3.8/site-packages/torch/nn/modules/linear.py", line 114, in forward return F.linear(input, self.weight, self.bias) RuntimeError: mat1 and mat2 shapes cannot be multiplied (1024x130344 and 4096x1)

Sleepychord commented 1 year ago

这报错看上去似乎只是代码问题,写错了有bug而已。

iamsile commented 1 year ago

不好意思,是输入的时候大小没对上,已经解决了