Atul Dhingra

1. ResNet 2. resnet_at_ilsvrc12_run.py 3. .pb 4. GPU 5. Whatever is defined here , run_local.sh nets/resnet_at_ilsvrc12_run.py

1. Yes, The only difference I see is that you are generating data with all zeros, and I generate it with ` np.random.rand`. I use batch size and average over...

@jiaxiang-wu DCP models https://drive.google.com/open?id=1NijcwZ-Cwd-Nqa73E2D5nTL_X2yhB32a UQTF Model https://drive.google.com/open?id=1LIYaJZclwBllEThoWZScj23Sq4_LkUxx

@zlacelle Did you also include Jetson AGX support ?

What's the recommended number and type of GPUs for finetuning this ?

This is the example I am running: ``` #### Code Generation example from transformers import AutoModelForCausalLM, AutoTokenizer checkpoint = "bigcode/starcoder" device = "cuda" # for GPU usage or "cpu" for...

@robertu7 Are you still running it with `compile=False` ?

It's non-deterministic, it gets triggered maybe 1/5 times running with the same task IDs (with Minimal React agent). I'll share it next time i see it

``` options = FinalRequestOptions( │ │ │ │ │ method='post', │ │ │ │ │ url='/gpt-4o/chat/completions', │ │ │ │ │ params={}, │ │ │ │ │ headers={ │ │...

Even I see an issue at ``` File "/app/openpi/models/model.py", line 312, in restore_params params = ckptr.restore( ``` when running the inference script(jupyter) provided in the README. It basically, gets killed...