Upload model files.

README.md

@@ -0,0 +1,45 @@
+---
+language:
+  - zh
+thumbnail: https://ckip.iis.sinica.edu.tw/files/ckip_logo.png
+tags:
+  - pytorch
+  - lm-head
+  - gpt2
+  - zh
+license: gpl-3.0
+---
+
+# CKIP GPT2 Tiny Chinese
+
+This project provides traditional Chinese transformers models (including ALBERT, BERT, GPT2) and NLP tools (including word segmentation, part-of-speech tagging, named entity recognition).
+
+這個專案提供了繁體中文的 transformers 模型（包含 ALBERT、BERT、GPT2）及自然語言處理工具（包含斷詞、詞性標記、實體辨識）。
+
+## Homepage
+
+- https://github.com/ckiplab/ckip-transformers
+
+## Contributers
+
+- [Mu Yang](https://muyang.pro) at [CKIP](https://ckip.iis.sinica.edu.tw) (Author & Maintainer)
+
+## Usage
+
+Please use BertTokenizerFast as tokenizer instead of AutoTokenizer.
+
+請使用 BertTokenizerFast 而非 AutoTokenizer。
+
+```
+from transformers import (
+  BertTokenizerFast,
+  AutoModel,
+)
+
+tokenizer = BertTokenizerFast.from_pretrained('bert-base-chinese')
+model = AutoModel.from_pretrained('ckiplab/gpt2-tiny-chinese')
+```
+
+For full usage and more information, please refer to https://github.com/ckiplab/ckip-transformers.
+
+有關完整使用方法及其他資訊，請參見 https://github.com/ckiplab/ckip-transformers 。

config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 101,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 102,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 312,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 4,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "tokenizer_class": "BertTokenizerFast",
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4109d34df76aabd608c5137a7fdba2a61065728aff9bf5093bc5a027d4eaff
+size 50619595

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-chinese"}