fix wrong tokenizer

config.json

@@ -1,31 +1,24 @@
 {
-  "_name_or_path": "THUDM/chatglm-6b",
+  "_name_or_path": "decapoda-research/llama-7b-hf",
   "architectures": [
-    "ChatGLMModel"
+    "LLaMAForCausalLM"
   ],
-  "auto_map": {
-    "AutoConfig": "THUDM/chatglm-6b--configuration_chatglm.ChatGLMConfig",
-    "AutoModel": "THUDM/chatglm-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSeq2SeqLM": "THUDM/chatglm-6b--modeling_chatglm.ChatGLMForConditionalGeneration"
-  },
-  "bos_token_id": 130004,
-  "eos_token_id": 130005,
-  "gmask_token_id": 130001,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
   "hidden_size": 4096,
-  "inner_hidden_size": 16384,
-  "layernorm_epsilon": 1e-05,
-  "mask_token_id": 130000,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
   "max_sequence_length": 2048,
-  "model_type": "chatglm",
+  "model_type": "llama",
   "num_attention_heads": 32,
-  "num_layers": 28,
-  "pad_token_id": 3,
-  "position_encoding_2d": true,
-  "pre_seq_len": null,
-  "prefix_projection": false,
-  "quantization_bit": 0,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.29.2",
   "use_cache": true,
-  "vocab_size": 130528
+  "vocab_size": 32000
 }

special_tokens_map.json

@@ -1,7 +1,23 @@
 {
-  "bos_token": "<sop>",
-  "eos_token": "<eop>",
-  "mask_token": "[MASK]",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,22 +1,33 @@
 {
-  "auto_map": {
-    "AutoTokenizer": [
-      "THUDM/chatglm-6b--tokenization_chatglm.ChatGLMTokenizer",
-      null
-    ]
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
   },
-  "bos_token": "<sop>",
-  "clean_up_tokenization_spaces": true,
-  "do_lower_case": false,
-  "end_token": "</s>",
-  "eos_token": "<eop>",
-  "gmask_token": "[gMASK]",
-  "mask_token": "[MASK]",
-  "model_max_length": 2048,
-  "num_image_tokens": 0,
-  "pad_token": "<pad>",
-  "padding_side": "left",
-  "remove_space": false,
-  "tokenizer_class": "ChatGLMTokenizer",
-  "unk_token": "<unk>"
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }