nullonesix

i tried running this CSGO agent on Jedi Academy: https://www.youtube.com/watch?v=kJIfxGQu4EA i was hoping to finetune it on Jedi Academy data but the data gathering code is somewhat CSGO specific (unlike...

adamw: step 5000: train loss 0.6171, val loss 1.6973 iter 5000: loss 0.8138, time 31669.98ms, mfu 4.02% sign descent: step 5000: train loss 1.0883, val loss 1.4821 iter 5000: loss...

typical protocol for windows-only games given lack of jax cuda support?

1

what's the typical way for doing RL for windows-only games when jax cuda has no support on windows?

AttributeError: 'numpy.ndarray' object has no attribute 'items'. Did you mean: 'item'?

1

i'm trying to connect dreamerv3 to a unity environment (which provides a gym interface) but i get the following error: ``` Logdir logdir\unity Create envs. config.envs: 1 make_env() suite ==...

trying to convert huggingface whisper model to pytorch

1

i used the converter here: https://github.com/pytorch-labs/gpt-fast/blob/main/scripts/convert_hf_checkpoint.py but i get this error when trying to convert my huggingface checkpoint: ``` swarms@dpm4:~/gpt-fast/scripts$ python3 converthf_checkpoint.py --checkpoint_dir /home/swarms/checkpoint-4000/ --model name large-v3 Traceback (most recent...

how to use a finetuned nonlocal model?

1

the build script and build.py expect a .pt file my checkpoint looks like: root@28f5bb431151:/app# ls checkpoint-4000/ config.json model-00001-of-00002.safetensors model.safetensors.index.json preprocessor_config.json scheduler.pt training_args.bin generation_config.json model-00002-of-00002.safetensors optimizer.pt rng_state.pth trainer_state.json what must i...

``` PS C:\Users\nullo\Documents\atc\wrn\whisper.rn> yarn example android yarn run v1.22.22 warning ..\..\package.json: No license field $ yarn --cwd example android warning ..\..\..\package.json: No license field $ react-native run-android (node:11592) [DEP0040] DeprecationWarning:...