first commit

README.md

@@ -1,3 +1,31 @@
-# mengzi-t5-base_a13579517675040768972685
+---
+language: 
+  - zh
+license: apache-2.0
+---
 
-mengzi-t5-base
+# Mengzi-T5 model (Chinese)
+Pretrained model on 300G Chinese corpus. 
+
+[Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese](https://arxiv.org/abs/2110.06696)
+
+## Usage
+```python
+from transformers import T5Tokenizer, T5ForConditionalGeneration
+
+tokenizer = T5Tokenizer.from_pretrained("Langboat/mengzi-t5-base")
+model = T5ForConditionalGeneration.from_pretrained("Langboat/mengzi-t5-base")
+```
+
+## Citation
+If you find the technical report or resource is useful, please cite the following technical report in your paper.
+```
+@misc{zhang2021mengzi,
+      title={Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese}, 
+      author={Zhuosheng Zhang and Hanqing Zhang and Keming Chen and Yuhang Guo and Jingyun Hua and Yulong Wang and Ming Zhou},
+      year={2021},
+      eprint={2110.06696},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}