Upload folder using huggingface_hub

README.md

@@ -45,8 +45,8 @@ Due to the sparse nature of the MoE layers, approximately **43% of the parameter
 
 Training is currently in progress on a single NVIDIA RTX 5000.
 
-* **Current Step:** 12,000
-* **Current Loss:** ~2.64
+* **Current Step:** 11,000
+* **Current Loss:** ~1.4167
 * **Dataset:** A subset of SlimPajama-627B
 
 > **⚠️ Performance Notice:** Aetheris is currently in a "proof-of-concept" state. While it generates coherent English syntax, it does not yet possess strong reasoning capabilities. It is intended for architectural analysis rather than downstream tasks.

checkpoints/checkpoint_17000_step.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86130f7b206e603a0777d82ce482d5cd08fd3168cdd5dd0a106fc71a145479f7
+size 3533562641