Upload 5 files

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "./pretrained/gpt2-chinese-cluecorpussmall",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -7,14 +8,17 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
+  "gradient_checkpointing": false,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
+  "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
-  "n_layer": 8,
+  "n_layer": 12,
   "n_positions": 1024,
+  "output_past": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -24,8 +28,15 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 320
+    }
+  },
+  "tokenizer_class": "BertTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.25.1",
   "use_cache": true,
-  "vocab_size": 25000
+  "vocab_size": 21128
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:676bafe3c4dde693e6387720922f1e2eddcfaa1b5633a273a651b424124214d8
-size 315188761
+oid sha256:e3236ef07d89dbfcb15ca86c3853330e6ed7fbe65e55cbea8c9ac3081680d262
+size 420912233

special_tokens_map.json

@@ -1,7 +1,7 @@
 {
   "cls_token": "[CLS]",
   "mask_token": "[MASK]",
-  "pad_token": "<pad>",
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,13 +1,15 @@
 {
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": false,
   "mask_token": "[MASK]",
   "max_len": 256,
-  "model_max_length": 256,
-  "name_or_path": "bert-base-chinese",
-  "pad_token": "<pad>",
+  "model_max_length": 1024,
+  "name_or_path": "./pretrained/gpt2-chinese-cluecorpussmall",
+  "never_split": null,
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
+  "special_tokens_map_file": "./pretrained/gpt2-chinese-cluecorpussmall/special_tokens_map.json",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",