Training Complete

config.json

@@ -0,0 +1,15 @@
+{
+  "architectures": [
+    "VLite3_5ForCausalLM"
+  ],
+  "dtype": "float32",
+  "hidden_size": 512,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 2048,
+  "model_type": "vlite3.5",
+  "num_hidden_layers": 11,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.1",
+  "use_cache": false,
+  "vocab_size": 40963
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.8.1",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6dc8f7148acd54c915d0a1cfd443433a8cee4cf209282766a910f56800bcc35
+size 254542420

tokenizer.json

@@ -80,7 +80,7 @@
   "pre_tokenizer": {
     "type": "Metaspace",
     "replacement": "▁",
-    "prepend_scheme": "always",
+    "prepend_scheme": "first",
     "split": false
   },
   "post_processor": {

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94eb9f6ed31f3eb07e308fdd234d9f923b60dd820a4b67583322c3acd83cabe3
+size 5265