Aman Rangapur
Aman Rangapur
> hi aman-17 i have the same problem could you solve it? I have used other package instead of nest2D Search for “maxrect” on github, clone it. I feel it...
You need to install a few pre-requisites which are mentioned in the read.me, pyaudio is one of them :)
The issue might be caused by accessing the dataset over the network, especially if you’re using HTML links to fetch data during training. Due to high network traffic or connection...
The initialization method for the OLMo 1B and 7B models has evolved over time. You can find the configuration for the initialization function in the [olmo/config.py](https://github.com/allenai/OLMo/blob/main/olmo/config.py) file, specifically in the...
Sorry for taking some time. We will get back to you.
Hey @jhxiang benchmark is available and you can try it out.
Hey @yungongzi, we haven’t tested our model on NPUs. However, if anyone in the community is interested in trying it out, we’d love to hear about their experience! If you...
@zhangtao103239 olmOCR is not yet merged to main branch of vllm. We will probably send a PR in upcoming weeks.
The difference in the tokens per second is due to the hardware and the restart behavior during training. The model was trained twice, once on AMD GPUs and once on...
Yes, as @Xu-pixel mentioned, adding --tp or --dp will do the job.