From bf3fc5e1c5b16851d1cf1501f0fb51dee4a9121e Mon Sep 17 00:00:00 2001
From: jeanpoll <jean-baptiste.polle@lautorite.qc.ca>
Date: Fri, 12 Mar 2021 09:25:57 -0500
Subject: [PATCH] first release

---
 .gitattributes          |  1 +
 config.json             | 38 ++++++++++++++++++++++++++++++++++++++
 pytorch_model.bin       |  3 +++
 sentencepiece.bpe.model |  3 +++
 special_tokens_map.json |  1 +
 tokenizer_config.json   |  1 +
 6 files changed, 47 insertions(+)
 create mode 100644 config.json
 create mode 100644 pytorch_model.bin
 create mode 100644 sentencepiece.bpe.model
 create mode 100644 special_tokens_map.json
 create mode 100644 tokenizer_config.json

diff --git a/.gitattributes b/.gitattributes
index 07f0db3..afbad77 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -14,3 +14,4 @@
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..09571de
--- /dev/null
+++ b/config.json
@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "camembert-base",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "eos_token_id": 6,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "LOC",
+    "2": "PER",
+    "3": "MISC",
+    "4": "ORG"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LOC": 1,
+    "MISC": 3,
+    "O": 0,
+    "ORG": 4,
+    "PER": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "type_vocab_size": 1,
+  "vocab_size": 32005
+}
diff --git a/pytorch_model.bin b/pytorch_model.bin
new file mode 100644
index 0000000..9305433
--- /dev/null
+++ b/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ac83b9b1ded370c85082c67735f7ef250a333aa37e6b3434b0dc0b210b1988
+size 440227047
diff --git a/sentencepiece.bpe.model b/sentencepiece.bpe.model
new file mode 100644
index 0000000..489f0a5
--- /dev/null
+++ b/sentencepiece.bpe.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
+size 810912
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..b74bdc9
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]}
\ No newline at end of file
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..092c1a2
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"], "model_max_length": 512, "name_or_path": "camembert-base"}
\ No newline at end of file