PandaGPT

PandaGPT copied to clipboard

Some weights of LlamaForCausalLM were not initialized from the model checkpoint at ../pretrained_ckpt/vicuna_ckpt/7b_v0/ and are newly initialized

1

!] load base configuration: config/base.yaml [!] load configuration from config/openllama_peft.yaml /root/anaconda3/envs/py310/lib/python3.10/site-packages/torchvision/transforms/_functional_video.py:6: UserWarning: The 'torchvision.transforms._functional_video' module is deprecated since 0.12 and will be removed in the future. Please use the 'torchvision.transforms.functional'...

Junnian

Leon1207

Junnian

Any plans to release this functionality for https://github.com/PKU-YuanGroup/LanguageBind/tree/main

abhimanyu891998

I have a question about the position format of the caption in the input data in the command data. For example, the following sentence in the paper, A video of...

liuxuannan

有人碰到这个问题吗？ ```AttributeError: 'OpenLLAMAPEFTModel' object has no attribute 'generate_one_sample'```

shuxiaobo

Saving Error

1

``` Time to load utils op: 0.000990152359008789 seconds 0%| | 0/908 [00:00

shuxiaobo

Deepspeed error: The server socket has failed to listen on any local network address. The server socket has failed to bind to [::]:28457 (errno: 98 - Address already in use).

1

Hi I am trining PandaGPT, I have 8 V100 GPUs. When I run ./scripts/train.sh, I got the following error: Traceback (most recent call last): File "user/test_panda/PandaGPT/code/train_sft.py", line 97, in main(**args)...

Dongzhikang

Does it support multi image input？

1

Do you currently support multi image input？ 请问支持多图输入吗

hangzeli08

请问我想在你们的基础上继续训练stage，应该怎么改openllama_peft_stage_1.json这个文件？

1

请问什么时候发布stage2的相关代码和配置文件呢，我现在想在你们训练好的基础上进行微调，应该改动哪些文件呢，如何修改openllama_peft_stage_1.json里面的参数呢，还是直接复制openllama_peft_stage_1.json到openllama_peft_stage_2.json就可以呢

hangzeli08