Training in progress, step 100

config.json

@@ -0,0 +1,14 @@
+{
+  "architectures": [
+    "SoraForSLM"
+  ],
+  "dtype": "float32",
+  "hidden_size": 1024,
+  "max_position_embeddings": 512,
+  "model_type": "sora_slm",
+  "num_heads": 32,
+  "num_layers": 32,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 23000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e5909f449a818c3b361c9cd9c8048d5679fae490ed00ec9dd5dae5cbdf4e24
+size 1802868184

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72714949e2b841ca642e601e30186e68d6af399e8eabb6286b818e559f2f415f
+size 5201