update

README.md

@@ -18,18 +18,11 @@ a series of experiments have been conducted to check the accuracy of the convers
 - Pytorch Conversion repo:  https://github.com/nghuyong/ERNIE-Pytorch
 
 ## How to use
-If you want to use ernie-3.0 series models, you need to add `task_type_id` to BERT model following this [MR](https://github.com/huggingface/transformers/pull/18686/files) 
-**OR** you can re-install the transformers from my changed branch.
-```bash
-pip uninstall transformers # optional
-pip install git+https://github.com/nghuyong/transformers@add_task_type_id # reinstall
-```
-Then you can load ERNIE-3.0 model as before:
 ```Python
-from transformers import BertTokenizer, BertModel
+from transformers import BertTokenizer, ErnieModel
 
 tokenizer = BertTokenizer.from_pretrained("nghuyong/ernie-3.0-mini-zh")
-model = BertModel.from_pretrained("nghuyong/ernie-3.0-mini-zh")
+model = ErnieModel.from_pretrained("nghuyong/ernie-3.0-mini-zh")
 ```
 
 ## Citation

config.json

@@ -13,8 +13,8 @@
     "use_task_id": true,
     "vocab_size": 40000,
     "layer_norm_eps": 1e-05,
-    "model_type": "bert",
+    "model_type": "ernie",
     "architectures": [
-        "BertModel"
+        "ErnieModel"
     ]
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd8aa94b5d744d8fa6ac8988b5f96bce3d9df5e729cf4315d77baa98b1095f3
-size 107238517
+oid sha256:f5ed30a38a7708656b2eb552ddeb58c787f82ab4cd6ed2a6258cdd2406e88150
+size 107238645