Added INDUS-SDE-GKR

model_architecture.txt

@@ -0,0 +1,51 @@
+ModernBertForSequenceClassification(
+  (model): ModernBertModel(
+    (embeddings): ModernBertEmbeddings(
+      (tok_embeddings): Embedding(50368, 768, padding_idx=50283)
+      (norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+      (drop): Dropout(p=0.0, inplace=False)
+    )
+    (layers): ModuleList(
+      (0): ModernBertEncoderLayer(
+        (attn_norm): Identity()
+        (attn): ModernBertAttention(
+          (Wqkv): Linear(in_features=768, out_features=2304, bias=False)
+          (rotary_emb): ModernBertRotaryEmbedding()
+          (Wo): Linear(in_features=768, out_features=768, bias=False)
+          (out_drop): Identity()
+        )
+        (mlp_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+        (mlp): ModernBertMLP(
+          (Wi): Linear(in_features=768, out_features=2304, bias=False)
+          (act): GELUActivation()
+          (drop): Dropout(p=0.0, inplace=False)
+          (Wo): Linear(in_features=1152, out_features=768, bias=False)
+        )
+      )
+      (1-21): 21 x ModernBertEncoderLayer(
+        (attn_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+        (attn): ModernBertAttention(
+          (Wqkv): Linear(in_features=768, out_features=2304, bias=False)
+          (rotary_emb): ModernBertRotaryEmbedding()
+          (Wo): Linear(in_features=768, out_features=768, bias=False)
+          (out_drop): Identity()
+        )
+        (mlp_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+        (mlp): ModernBertMLP(
+          (Wi): Linear(in_features=768, out_features=2304, bias=False)
+          (act): GELUActivation()
+          (drop): Dropout(p=0.0, inplace=False)
+          (Wo): Linear(in_features=1152, out_features=768, bias=False)
+        )
+      )
+    )
+    (final_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+  )
+  (head): ModernBertPredictionHead(
+    (dense): Linear(in_features=768, out_features=768, bias=False)
+    (act): GELUActivation()
+    (norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+  )
+  (drop): Dropout(p=0.0, inplace=False)
+  (classifier): Linear(in_features=768, out_features=3240, bias=True)
+)

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e148719ab875ff00516bfe4758c0d886ccf1c4590ce8ab8c356272ac9057110
+size 5432