Upload gpt_modern_1b_class.script.pt

JiRackPyTorch 1B Model Definition
FIXED: Implemented numerical stability improvements (FP32 Attention, better weight initialization)
FIXED: Corrected gradient checkpointing usage.
FIXED: Added Dropout layers.
FIXED: Auto-detect device for RoPE buffer handling.

gpt_modern_1b_class.script.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06ce7a6afd8ee4ab288933eb4e6047f7950d1032e58ee258a78ec7c6538bc824
-size 4715704946
+oid sha256:13c3b7609d8e485c42897e73243a42e9461ae75e3340e2d7be4a8761c216b6de
+size 4715746362