smallest tokenizer and correct token indices

config.json

@@ -5,7 +5,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "embd_pdrop": 0.0,
-  "eos_token_id": 2,
+  "eos_token_id": 32000,
   "hidden_act": "silu",
   "hidden_size": 64,
   "initializer_range": 0.02,
@@ -15,8 +15,9 @@
   "num_attention_heads": 1,
   "num_hidden_layers": 4,
   "num_key_value_heads": 1,
+  "oes_token_id": 2,
   "original_max_position_embeddings": 4096,
-  "pad_token_id": 2,
+  "pad_token_id": 3,
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
@@ -26,5 +27,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.1",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 25
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 2,
+  "eos_token_id": 32000,
+  "pad_token_id": 3,
   "transformers_version": "4.46.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa21b14a9c4cbcc0bd141d83cfe99a35de4544d5001db5a1239ebe65ef78b07
-size 8328624
+oid sha256:f881eee8cf3215a38fd73d53fdb75fd306d6337975b6ce7f666653499f285740
+size 142920

special_tokens_map.json

@@ -1,27 +1,48 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,10 +1,7 @@
 {
-  "add_bos_token": false,
-  "add_eos_token": false,
-  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -12,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -20,112 +17,42 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "32000": {
-      "content": "<|endoftext|>",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32001": {
-      "content": "<|assistant|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32002": {
-      "content": "<|placeholder1|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32003": {
-      "content": "<|placeholder2|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32004": {
-      "content": "<|placeholder3|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32005": {
-      "content": "<|placeholder4|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32006": {
-      "content": "<|system|>",
+    "3": {
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32007": {
-      "content": "<|end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32008": {
-      "content": "<|placeholder5|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32009": {
-      "content": "<|placeholder6|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32010": {
-      "content": "<|user|>",
+    "4": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "legacy": false,
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "left",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "max_length": 10,
+  "model_max_length": 10,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
 }