Kada
Kada
@odusseys I have the same problem
@yisuanwang 谢谢你的回答 是下载这个数据集吗 https://tri-ml-public.s3.amazonaws.com/datasets/views_release.tar.gz 怎么下载部分数据集
我看到File and versions中有.json.gz文件和.glb文件，我是只需要下载一些.glb文件用来跑通训练步骤吗 不好意思我是初学者，不知道怎么用自定义数据来训练，您可以告诉我大致的步骤吗 万望得到您的回答~ 感谢~
好的好的 感谢
@YJ-142150 Same question. Have you solved it yet?
@gitsawww Do you know how to use custom data to train now?
@sandeepjangir07 I have the same question
@betterze @wangzhen699 @whiteYi May I ask if you have resolved this issue. I also want to use ddim to accelerate the sampling speed in SR3. But due to my knowledge,...
@ZMXJJ @tc-mb Similar question. Does this llamafactory finetune script for MiniCPM-V-4_5 support multimodal training, such as having images and videos in one message and audio in another message? `[ {...
@tc-mb I used the following code with the MiniCPM-V-4_5 model, and encountered the same error: answer = model.chat( File "/root/.cache/huggingface/modules/transformers_modules/model/modeling_minicpmv.py", line 361, in chat copy_msgs = deepcopy(msgs) File "/opt/conda/envs/minicpm_v4_5/lib/python3.9/copy.py", line...