From d6fc34b45984ead95fb59c3b0758347fcb95603c Mon Sep 17 00:00:00 2001
From: Julien Chaumond <chaumond@gmail.com>
Date: Fri, 31 Jan 2020 17:10:04 -0500
Subject: [PATCH] [model_cards] add mine

---
 .../julien-c/bert-xsmall-dummy/README.md      | 25 +++++++++
 model_cards/julien-c/dummy-unknown/README.md  | 52 +++++++++++++++++++
 2 files changed, 77 insertions(+)
 create mode 100644 model_cards/julien-c/bert-xsmall-dummy/README.md
 create mode 100644 model_cards/julien-c/dummy-unknown/README.md

diff --git a/model_cards/julien-c/bert-xsmall-dummy/README.md b/model_cards/julien-c/bert-xsmall-dummy/README.md
new file mode 100644
index 0000000000..36eef62327
--- /dev/null
+++ b/model_cards/julien-c/bert-xsmall-dummy/README.md
@@ -0,0 +1,25 @@
+## How to build a dummy model
+
+
+```python
+from transformers.configuration_bert import BertConfig
+from transformers.modeling_bert import BertForMaskedLM
+from transformers.modeling_tf_bert import TFBertForMaskedLM
+from transformers.tokenization_bert import BertTokenizer
+
+
+SMALL_MODEL_IDENTIFIER = "julien-c/bert-xsmall-dummy"
+DIRNAME = "./bert-xsmall-dummy"
+
+config = BertConfig(10, 20, 1, 1, 40)
+
+model = BertForMaskedLM(config)
+model.save_pretrained(DIRNAME)
+
+tf_model = TFBertForMaskedLM.from_pretrained(DIRNAME, from_pt=True)
+tf_model.save_pretrained(DIRNAME)
+
+# Slightly different for tokenizer.
+# tokenizer = BertTokenizer.from_pretrained(DIRNAME)
+# tokenizer.save_pretrained()
+```
diff --git a/model_cards/julien-c/dummy-unknown/README.md b/model_cards/julien-c/dummy-unknown/README.md
new file mode 100644
index 0000000000..9cdc3d2437
--- /dev/null
+++ b/model_cards/julien-c/dummy-unknown/README.md
@@ -0,0 +1,52 @@
+
+```python
+import json
+import os
+from transformers.configuration_roberta import RobertaConfig
+from transformers import RobertaForMaskedLM, TFRobertaForMaskedLM
+
+DIRNAME = "./dummy-unknown"
+
+
+config = RobertaConfig(10, 20, 1, 1, 40)
+
+model = RobertaForMaskedLM(config)
+model.save_pretrained(DIRNAME)
+
+tf_model = TFRobertaForMaskedLM.from_pretrained(DIRNAME, from_pt=True)
+tf_model.save_pretrained(DIRNAME)
+
+# Tokenizer:
+
+vocab = [
+    "l",
+    "o",
+    "w",
+    "e",
+    "r",
+    "s",
+    "t",
+    "i",
+    "d",
+    "n",
+    "\u0120",
+    "\u0120l",
+    "\u0120n",
+    "\u0120lo",
+    "\u0120low",
+    "er",
+    "\u0120lowest",
+    "\u0120newer",
+    "\u0120wider",
+    "<unk>",
+]
+vocab_tokens = dict(zip(vocab, range(len(vocab))))
+merges = ["#version: 0.2", "\u0120 l", "\u0120l o", "\u0120lo w", "e r", ""]
+
+vocab_file = os.path.join(DIRNAME, "vocab.json")
+merges_file = os.path.join(DIRNAME, "merges.txt")
+with open(vocab_file, "w", encoding="utf-8") as fp:
+    fp.write(json.dumps(vocab_tokens) + "\n")
+with open(merges_file, "w", encoding="utf-8") as fp:
+    fp.write("\n".join(merges))
+```