Peng Liu

inference error

1

The command i used is: **python train_net.py --config-file configs/sparse_inst_r50_base.yaml --num-gpus 8 OUTPUT_DIR output/sparse_inst_r50_base2** Traceback (most recent call last): File "/hd-4t/peng/anaconda3/envs/sparseInst/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 59, in _wrap fn(i, *args) File "/hd-4t/peng/anaconda3/envs/sparseInst/lib/python3.8/site-packages/detectron2/engine/launch.py", line 126,...

Question about the tokens/per second/GPU

1

### ❓ The question Thanks for your great work. I have a question about the tokens/second/GPU when training the 7B model. I checked your [TRAINLOG.md](https://github.com/allenai/OLMo/blob/main/docs/TRAINLOG.md#:~:text=yet%20we%20saw-,1200,-tokens/second/GPU), it saids the tokens/second/GPU for...

Train the model for track 1

3

Hi I'm trying to practice and redo your work on AIcity track1. I saw this is a detailed guidance about how to train a ReID model using the AIcity track2...

@wenhuchen Hi, I noticed you posted the ChatGPT score [here](https://github.com/TIGER-AI-Lab/Program-of-Thoughts/blob/main/benchmark.md#:~:text=Params-,GSM8K,-TheoremQA). Could you please let me know which version of ChatGPT was used to obtain this score? Thank you!

Enhancing SAM3 with VLM-FO1 for Complex Text Label Tasks

1

First of all, thanks to the **SAM3** team for your excellent work on text-conditioned segmentation. SAM3's powerful capabilities have been instrumental in enabling this integration. I'm excited to share a...