Chaos

RuntimeWarning: Mean of empty slice. return _methods._mean(a, axis=axis, dtype=dtype,

2

Epoch 5/10 Best val. mIoU=0.0000 Loss C.=0.2363 Loss BB.=0.4493 Loss Seg.=1.7465: 50% 1480/2960 [01:15

IndexError: tuple index out of range

1

Traceback (most recent call last): File "main.py", line 150, in model_wrapper.test() File "/usr/local/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 49, in decorate_no_grad return func(*args, **kwargs) File "/content/drive/MyDrive/Cell-DETR/model_wrapper.py", line 421, in test misc.plot_instance_segmentation_labels( File "/content/drive/MyDrive/Cell-DETR/misc.py", line...

How to use gemma for multi-round conversations

3

Thank a lot for your great work！ I deployed gemma-2b locally. I would like to understand how to have multiple rounds of dialog effectively. I searched the internet and found...

“参数命名不同”：Huggingface上的CLIP模型和GITHUB上的 CLIP模型 参数命名不同。 请问，这种命名不同，会影响，模型效果吗？

手动修改ChineseCLIPVisionModel to ChineseCLIPVisionModelWithProjection 失败。

1

import torch import torch.nn as nn visual_projection = nn.Linear(768, 512, bias=False) embeds = visual_projection(pooled_output) 我人为添加了一个映射层，发现和ChineseCLIPModel求出来的编码不一样。

ChineseCLIPVisionModel in huggingface can used?

3

(cropa) root@v3-custom-667bbc1c8454e110f8bda977-7ldhs:/# python /data/codes/test.py Downloading config.json: 3.01kB [00:00, 215kB/s] Downloading pytorch_model.bin: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 753M/753M [00:58

Very nice work, thanks for your efforts with open source. I notice that you are combining multiple datasets to train for one large dataset. Engineering wise, how did you combine...

Does the model support Chinese language, I learnt about your organisation from Chinese CLIP.

请问如何控制故事结束呢？

1

请问如何控制故事结束呢？ 代码里面好像使用while写的，会一直写下去吗

非常有趣的工作！！！ 我调用了本地部署的大模型，生成了一些文字后。成功爆内存了哈哈哈哈