-
### 是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?
- [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
### 该问题是否在FAQ中有解答? | Is there an existing ans…
-
Very interesting work so that I can learn a lot! But I have a question for the author when I execute the following code to install a custom transformer:
cd dep/transformers_custom/transformers-4.31…
-
Hi, me again!
I'm trying to train the OpenVLA model on BridgeData V2 with the script you provided in the README.
```bash
# Train VLA on BridgeData V2 with the Prismatic DINO-SigLIP 224px Backbo…
-
I am using the following bash script and command with the mmbench dataset for replication purposes. The model file `./checkpoints-lora-total/merged_Bunny-phi-siglip` was downloaded from this link: […
-
### Your question
Hello,
Is it possible to use the same model to generate vision and text embeddings. Seems like models like CLIP and SigLIP should support this but using pipelines like this:
`…
-
Excellent work! BTW, Does the model support Chinese?
-
你好,我在使用你们代码进行训练时发现,使用S2增加图像的输入分辨率的方式的训练速度比不使用S2慢4倍,这种现象正常吗?
-
作者好,非常感谢你的开源。我有两个疑问想咨询下
**1. convnext 的 drop path 问题**
convnext 的 drop path 是 0.1,虽然你在训练时候设置的是不训练,但是这个路径还是会执行的。原则上在训练时候,convnext 要设置为 eval 模式吧? 我没有找到相关代码,有点奇怪,想了解下
**2. 代码鲁棒性问题**
如果是 clip+…
-
我尝试在自己的数据集上进行了微调,但是当我微调后不论是lora还是全量,在尝试输入图片的时候都出现了报错:
***
RuntimeError: mat1 and mat2 shapes cannot be multiplied (729x1152 and 3456x4096)
***
根据调用堆栈,可能是我的projector维度异常发生了改变
这是我的微调配置文件:
#!/bin/…
htesd updated
2 months ago
-
楼主有遇到过类似的情况吗?
{'loss': 0.0, 'learning_rate': 0.001435114503816794, 'epoch': 0.02}
2%|██…