叶加博

The prompt used for AndroidWorld can be found in Qwen2.5-VL/cookbooks/mobile_agent.ipynb. Notably, to fit the action space in AndroidWorld evaluation, we add a new action `answer`. Therefore, there are some modifications...

> [@Timothyxxx](https://github.com/Timothyxxx) [@LukeForeverYoung](https://github.com/LukeForeverYoung) Thanks for your reply. I have two questions: > > 1. Tasks in the AndoridWorld or other benchmarks involve information retrieval and require the history to contain...

Does this code span work for you? ``` import torch from transformers import AutoConfig, AutoModel model_path = 'mPLUG/mPLUG-Owl3-7B-240728' config = AutoConfig.from_pretrained(model_path, trust_remote_code=True) print(config) # model = mPLUGOwl3Model(config).cuda().half() model = AutoModel.from_pretrained(model_path,...

Hi, the accuracy of most large language models can be affected by the prompt. We will release the evaluation pipeline in the coming days for easy reproducibility of the results....

> > Hi, the accuracy of most large language models can be affected by the prompt. We will release the evaluation pipeline in the coming days for easy reproducibility of...

We do not have a development machine with multiple GPUs, so this scenario has not been fully tested. I suspect that the issue may be due to the visual features...

Refer to this issue, #725 ```plain Before answering, explain your reasoning step-by-step in tags, and insert them before the XML tags.\nAfter answering, summarize your action in tags, and insert them...

Here is an example message we collected from the evaluation of qwenvl on Android World, consisting of a system prompt, user query, and model response. You can do some modifications...

Hi, we are still refining the evaluation framework code to remove dependencies on some internal packages. Here, I've copied the main part of the grounding evaluation code, which should be...

你好，我把当时进行aitz评测的相关代码拆出来，贴在这条[gist](https://gist.github.com/LukeForeverYoung/274a073ca77c9dc46022cb8cc5382223)里，可以参考一下。