tangledgroup
/

tangled-llama-33m-32k-base-v0.1

Text Generation

Inference Endpoints

Model card Files Files and versions Community

mtasic85 commited on Sep 25, 2024

Commit

2394c59

·

1 Parent(s): 0c8be57

model

Files changed (2) hide show

scripts/model.yaml +2 -1
scripts/requirements-lit.in +2 -1

scripts/model.yaml CHANGED Viewed

@@ -99,7 +99,8 @@ eval:
 # Optimizer-related arguments
 optimizer:
-  class_path: torch.optim.AdamW
   init_args:
     #   (type: float, default: 0.001)

 # Optimizer-related arguments
 optimizer:
+  # class_path: torch.optim.AdamW
+  class_path: grokadamw.GrokAdamW
   init_args:
     #   (type: float, default: 0.001)

scripts/requirements-lit.in CHANGED Viewed

@@ -6,4 +6,5 @@ transformers
 bitsandbytes
 wandb
 litgpt[all]
-litdata

 bitsandbytes
 wandb
 litgpt[all]
+litdata
+grokadamw