Upload 6 files

TokenConvert.py

@@ -0,0 +1,30 @@
+# from tokenization_gptpangu import GPTPanguTokenizer
+# import json
+#
+# tokenizer = GPTPanguTokenizer.from_pretrained(".")
+# with open("tokenizer.json",encoding="utf-8") as f:
+#     cofig = json.load(f)
+#
+#
+# vocab_file = "vocab.vocab"
+#
+# f = open(vocab_file, 'r', encoding="utf-8")
+# lines = f.readlines()
+# vocab = []
+# for line in enumerate(lines):
+#     key = line[1].split('\t')[0]
+#     pair = [key,line[0]]
+#     vocab.append(pair)
+#
+# cofig['model']['vocab'] = vocab
+#
+# with open("new_tokenizer.json","w",encoding="utf-8") as w:
+#     d = json.dumps(cofig)
+#     w.write(d)
+#
+# print("ok")
+
+from transformers import  AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained(".")
+
+

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>",  "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": [ "<eod>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18857e86783e50cfcaa0bc3c043fb4e9b5f240b885d2870ea593ee69b44f7a3a
+size 879697

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": false, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>",  "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": [ "<eod>"], "special_tokens_map_file": null, "name_or_path": "TsinghuaAI/CPM-Generate", "tokenizer_class": "CpmTokenizer"}