Zhuoheng Li
Zhuoheng Li
Hi @RdoubleA, Currently I am training llava with [Xtuner](https://github.com/InternLM/xtuner), which is similar to torchtune. They support finetuning, evaluation and deployment of llava models (we can easily add custom modification to...
@davidluciolu 您可以参考#376
Hello, I am doing similar thing with a smaller version of LLaVA (around 2.2B) [link](https://huggingface.co/StarCycle/llava-clip-internlm2-1_8b-pretrain-v1). But you can also look at [ROSGPT_vision](https://github.com/bilel-bj/ROSGPT_Vision)
I will use LMDeploy for inference (but havent tries it on devices like Jetson)...
If other researchers have such plan, please reply and we may work together!
> @StarCycle This is an amazing project but, I'm just going to try to load it 8bit (i don't even know if it will work). I have a 4070ti, never...
我也遇到这样的问题。我下载的是coco数据集的images.zip文件，win端可以下载，linux端报错“文件不合法或者被禁止下载”
Btw it will be great if you can share the loss curve in the report! I think the biggest problem of LLaVA based models is avoiding overfitting, since they only...
重装cuda到12.4，重装pytorch还是不行 ··· PS C:\Users\marti> lmdeploy check_env sys.platform: win32 Python: 3.9.12 (tags/v3.9.12:b28265d, Mar 23 2022, 23:52:46) [MSC v.1929 64 bit (AMD64)] CUDA available: True MUSA available: False numpy_random_seed: 2147483648 GPU 0:...
Still looking forward!