Refresh: aligned EOS/PAD + generation_config

config.json

@@ -7,7 +7,7 @@
   "attn_pdrop": 0.1,
   "bos_token_id": 1,
   "embd_pdrop": 0.1,
-  "eos_token_id": 1,
+  "eos_token_id": 3,
   "initializer_range": 0.01,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 1,
+  "eos_token_id": 3,
   "pad_token_id": 0,
   "transformers_version": "4.50.3"
 }

special_tokens_map.json

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }