Updated Model

Browse files

Files changed (5) hide show

config.json +9 -9
generation_config.json +1 -1
special_tokens_map.json +15 -1
tokenizer.json +0 -0
tokenizer_config.json +128 -3

config.json CHANGED Viewed

@@ -3,18 +3,18 @@
     "CustomTransformerModel"
   ],
   "bos_token_id": 2,
-  "d_ff": 3072,
-  "d_model": 768,
-  "dropout": 0.1,
   "eos_token_id": 3,
-  "max_position_embeddings": 512,
   "model_type": "miscovery",
-  "num_decoder_layers": 12,
-  "num_encoder_layers": 12,
-  "num_heads": 12,
   "pad_token_id": 0,
   "torch_dtype": "float32",
-  "transformers_version": "4.51.3",
   "use_flash_attn": true,
-  "vocab_size": 100000
 }

     "CustomTransformerModel"
   ],
   "bos_token_id": 2,
+  "d_ff": 2048,
+  "d_model": 512,
+  "dropout": 0.05,
   "eos_token_id": 3,
+  "max_position_embeddings": 300,
   "model_type": "miscovery",
+  "num_decoder_layers": 8,
+  "num_encoder_layers": 8,
+  "num_heads": 8,
   "pad_token_id": 0,
   "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
   "use_flash_attn": true,
+  "vocab_size": 50000
 }

generation_config.json CHANGED Viewed

@@ -3,5 +3,5 @@
   "bos_token_id": 2,
   "eos_token_id": 3,
   "pad_token_id": 0,
-  "transformers_version": "4.51.3"
 }

   "bos_token_id": 2,
   "eos_token_id": 3,
   "pad_token_id": 0,
+  "transformers_version": "4.35.2"
 }

special_tokens_map.json CHANGED Viewed

@@ -2,7 +2,21 @@
   "additional_special_tokens": [
     "[LANG_EN]",
     "[LANG_AR]",
-    "[LANG_AR_EG]"
   ],
   "cls_token": {
     "content": "[CLS]",

   "additional_special_tokens": [
     "[LANG_EN]",
     "[LANG_AR]",
+    "[LANG_AR_EG]",
+    "[TRANSLATION]",
+    "[SUMMARIZATION]",
+    "[PARAPHRASING]",
+    "[INSTRUCTIONS]",
+    "[CALCULATE]",
+    "[REORDER]",
+    "[QUESTION]",
+    "[ANSWER]",
+    "[CHOICES]",
+    "[START_OPTION]",
+    "[END_OPTION]",
+    "[REASONING]",
+    "[START_THINKING]",
+    "[END_THINKING]"
   ],
   "cls_token": {
     "content": "[CLS]",

tokenizer.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -63,20 +63,145 @@
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
   "additional_special_tokens": [
     "[LANG_EN]",
     "[LANG_AR]",
-    "[LANG_AR_EG]"
   ],
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "tokenizer_class": "PreTrainedTokenizer",
   "unk_token": "[UNK]"
 }

       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "8": {
+      "content": "[TRANSLATION]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "[SUMMARIZATION]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "[PARAPHRASING]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "[INSTRUCTIONS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "[CALCULATE]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "[REORDER]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "[QUESTION]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "[ANSWER]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "[CHOICES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "[START_OPTION]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "[END_OPTION]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "[REASONING]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "[START_THINKING]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "[END_THINKING]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
     "[LANG_EN]",
     "[LANG_AR]",
+    "[LANG_AR_EG]",
+    "[TRANSLATION]",
+    "[SUMMARIZATION]",
+    "[PARAPHRASING]",
+    "[INSTRUCTIONS]",
+    "[CALCULATE]",
+    "[REORDER]",
+    "[QUESTION]",
+    "[ANSWER]",
+    "[CHOICES]",
+    "[START_OPTION]",
+    "[END_OPTION]",
+    "[REASONING]",
+    "[START_THINKING]",
+    "[END_THINKING]"
   ],
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "[UNK]"
 }