fix tokenizer settings for step 2038000

config.json

@@ -2,9 +2,9 @@
   "architectures": [
     "UMT5ForConditionalGeneration"
   ],
-  "d_ff": 5120,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 2048,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -15,16 +15,16 @@
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "umt5",
-  "num_decoder_layers": 24,
-  "num_heads": 32,
-  "num_layers": 24,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "scalable_attention": true,
   "tie_word_embeddings": false,
-  "tokenizer_class": "T5TokenizerFast",
+  "tokenizer_class": "LlamaTokenizerFast",
   "torch_dtype": "bfloat16",
   "transformers_version": "4.31.0",
   "use_cache": true,

special_tokens_map.json

@@ -103,6 +103,5 @@
   ],
   "bos_token": "<s>",
   "eos_token": "</s>",
-  "pad_token": "<pad>",
   "unk_token": "<unk>"
 }

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,113 +1,137 @@
 {
-  "additional_special_tokens": [
-    "<extra_id_0>",
-    "<extra_id_1>",
-    "<extra_id_2>",
-    "<extra_id_3>",
-    "<extra_id_4>",
-    "<extra_id_5>",
-    "<extra_id_6>",
-    "<extra_id_7>",
-    "<extra_id_8>",
-    "<extra_id_9>",
-    "<extra_id_10>",
-    "<extra_id_11>",
-    "<extra_id_12>",
-    "<extra_id_13>",
-    "<extra_id_14>",
-    "<extra_id_15>",
-    "<extra_id_16>",
-    "<extra_id_17>",
-    "<extra_id_18>",
-    "<extra_id_19>",
-    "<extra_id_20>",
-    "<extra_id_21>",
-    "<extra_id_22>",
-    "<extra_id_23>",
-    "<extra_id_24>",
-    "<extra_id_25>",
-    "<extra_id_26>",
-    "<extra_id_27>",
-    "<extra_id_28>",
-    "<extra_id_29>",
-    "<extra_id_30>",
-    "<extra_id_31>",
-    "<extra_id_32>",
-    "<extra_id_33>",
-    "<extra_id_34>",
-    "<extra_id_35>",
-    "<extra_id_36>",
-    "<extra_id_37>",
-    "<extra_id_38>",
-    "<extra_id_39>",
-    "<extra_id_40>",
-    "<extra_id_41>",
-    "<extra_id_42>",
-    "<extra_id_43>",
-    "<extra_id_44>",
-    "<extra_id_45>",
-    "<extra_id_46>",
-    "<extra_id_47>",
-    "<extra_id_48>",
-    "<extra_id_49>",
-    "<extra_id_50>",
-    "<extra_id_51>",
-    "<extra_id_52>",
-    "<extra_id_53>",
-    "<extra_id_54>",
-    "<extra_id_55>",
-    "<extra_id_56>",
-    "<extra_id_57>",
-    "<extra_id_58>",
-    "<extra_id_59>",
-    "<extra_id_60>",
-    "<extra_id_61>",
-    "<extra_id_62>",
-    "<extra_id_63>",
-    "<extra_id_64>",
-    "<extra_id_65>",
-    "<extra_id_66>",
-    "<extra_id_67>",
-    "<extra_id_68>",
-    "<extra_id_69>",
-    "<extra_id_70>",
-    "<extra_id_71>",
-    "<extra_id_72>",
-    "<extra_id_73>",
-    "<extra_id_74>",
-    "<extra_id_75>",
-    "<extra_id_76>",
-    "<extra_id_77>",
-    "<extra_id_78>",
-    "<extra_id_79>",
-    "<extra_id_80>",
-    "<extra_id_81>",
-    "<extra_id_82>",
-    "<extra_id_83>",
-    "<extra_id_84>",
-    "<extra_id_85>",
-    "<extra_id_86>",
-    "<extra_id_87>",
-    "<extra_id_88>",
-    "<extra_id_89>",
-    "<extra_id_90>",
-    "<extra_id_91>",
-    "<extra_id_92>",
-    "<extra_id_93>",
-    "<extra_id_94>",
-    "<extra_id_95>",
-    "<extra_id_96>",
-    "<extra_id_97>",
-    "<extra_id_98>",
-    "<extra_id_99>"
-  ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "<unk>",
-  "unk_token": "<unk>",
-  "extra_ids": 100,
+  "add_bos_token": false,
+  "add_eos_token": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
   "model_max_length": 512,
+  "pad_token": null,
+  "padding_side": "right",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "T5Tokenizer"
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "additional_special_tokens": [
+    "<extra_id_99>",
+    "<extra_id_98>",
+    "<extra_id_97>",
+    "<extra_id_96>",
+    "<extra_id_95>",
+    "<extra_id_94>",
+    "<extra_id_93>",
+    "<extra_id_92>",
+    "<extra_id_91>",
+    "<extra_id_90>",
+    "<extra_id_89>",
+    "<extra_id_88>",
+    "<extra_id_87>",
+    "<extra_id_86>",
+    "<extra_id_85>",
+    "<extra_id_84>",
+    "<extra_id_83>",
+    "<extra_id_82>",
+    "<extra_id_81>",
+    "<extra_id_80>",
+    "<extra_id_79>",
+    "<extra_id_78>",
+    "<extra_id_77>",
+    "<extra_id_76>",
+    "<extra_id_75>",
+    "<extra_id_74>",
+    "<extra_id_73>",
+    "<extra_id_72>",
+    "<extra_id_71>",
+    "<extra_id_70>",
+    "<extra_id_69>",
+    "<extra_id_68>",
+    "<extra_id_67>",
+    "<extra_id_66>",
+    "<extra_id_65>",
+    "<extra_id_64>",
+    "<extra_id_63>",
+    "<extra_id_62>",
+    "<extra_id_61>",
+    "<extra_id_60>",
+    "<extra_id_59>",
+    "<extra_id_58>",
+    "<extra_id_57>",
+    "<extra_id_56>",
+    "<extra_id_55>",
+    "<extra_id_54>",
+    "<extra_id_53>",
+    "<extra_id_52>",
+    "<extra_id_51>",
+    "<extra_id_50>",
+    "<extra_id_49>",
+    "<extra_id_48>",
+    "<extra_id_47>",
+    "<extra_id_46>",
+    "<extra_id_45>",
+    "<extra_id_44>",
+    "<extra_id_43>",
+    "<extra_id_42>",
+    "<extra_id_41>",
+    "<extra_id_40>",
+    "<extra_id_39>",
+    "<extra_id_38>",
+    "<extra_id_37>",
+    "<extra_id_36>",
+    "<extra_id_35>",
+    "<extra_id_34>",
+    "<extra_id_33>",
+    "<extra_id_32>",
+    "<extra_id_31>",
+    "<extra_id_30>",
+    "<extra_id_29>",
+    "<extra_id_28>",
+    "<extra_id_27>",
+    "<extra_id_26>",
+    "<extra_id_25>",
+    "<extra_id_24>",
+    "<extra_id_23>",
+    "<extra_id_22>",
+    "<extra_id_21>",
+    "<extra_id_20>",
+    "<extra_id_19>",
+    "<extra_id_18>",
+    "<extra_id_17>",
+    "<extra_id_16>",
+    "<extra_id_15>",
+    "<extra_id_14>",
+    "<extra_id_13>",
+    "<extra_id_12>",
+    "<extra_id_11>",
+    "<extra_id_10>",
+    "<extra_id_9>",
+    "<extra_id_8>",
+    "<extra_id_7>",
+    "<extra_id_6>",
+    "<extra_id_5>",
+    "<extra_id_4>",
+    "<extra_id_3>",
+    "<extra_id_2>",
+    "<extra_id_1>",
+    "<extra_id_0>"
+  ]
 }