correct tokenizer files and configs

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "_name_or_path": "codellama/CodeLlama-7b-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,7 +9,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
+  "max_position_embeddings": 16384,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -17,9 +17,10 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 1000000,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.31.0.dev0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.0.dev0",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 32016
 }

generation_config.json

@@ -1,10 +1,6 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 1,
-  "do_sample": true,
   "eos_token_id": 2,
-  "pad_token_id": 0,
-  "temperature": 0.6,
-  "max_length": 4096,
-  "top_p": 0.9,
-  "transformers_version": "4.31.0.dev0"
+  "transformers_version": "4.33.0.dev0"
 }

special_tokens_map.json

@@ -2,21 +2,21 @@
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -32134,7 +32134,23 @@
       "왕": 31996,
       "收": 31997,
       "弘": 31998,
-      "给": 31999
+      "给": 31999,
+      "▁<SU": 32000,
+      "▁<SUF": 32001,
+      "▁<PRE": 32002,
+      "▁<M": 32003,
+      "▁<MID": 32004,
+      "▁<E": 32005,
+      "▁<EOT": 32006,
+      "▁<PRE>": 32007,
+      "▁<SUF>": 32008,
+      "▁<MID>": 32009,
+      "▁<EOT>": 32010,
+      "▁<EOT><EOT>": 32011,
+      "▁<EOT><EOT><EOT>": 32012,
+      "▁<EOT><EOT><EOT><EOT>": 32013,
+      "▁<EOT><EOT><EOT><EOT><EOT>": 32014,
+      "▁<EOT><EOT><EOT><EOT><EOT><EOT>": 32015
     },
     "merges": [
       "▁ t",
@@ -93385,7 +93401,18 @@
       "▁▁▁▁▁▁▁▁▁ ▁▁▁▁▁▁",
       "▁▁▁▁▁▁▁ ▁▁▁▁▁▁▁▁",
       "▁▁▁▁▁▁▁▁▁▁▁ ▁▁▁▁",
-      "▁ ▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
+      "▁ ▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "▁< SU",
+      "▁<SU F",
+      "▁< PRE",
+      "▁< M",
+      "▁<M ID",
+      "▁< E",
+      "▁<E OT",
+      "▁<PRE >",
+      "▁<SUF >",
+      "▁<MID >",
+      "▁<EOT >"
     ]
   }
 }

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -5,7 +5,7 @@
     "__type": "AddedToken",
     "content": "<s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
@@ -14,21 +14,20 @@
     "__type": "AddedToken",
     "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "legacy": false,
+  "legacy": null,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
-  "padding_side": "right",
   "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_class": "CodeLlamaTokenizer",
   "unk_token": {
     "__type": "AddedToken",
     "content": "<unk>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }