first submitted version

README.md

@@ -1,3 +1,15 @@
 ---
 license: apache-2.0
 ---
+language:
+- en
+- hi
+---
+
+# en-hi-codemixed
+
+This is a masked language model, based on the CamemBERT model architecture. 
+en-hi-codemixed model was trained from scratch on English, Hindi, and codemixed English-Hindi
+corpora for 40 epochs.
+The corpora used consists of primarily web crawled data, including codemixed tweets, and focuses on conversational
+language and covid-19 pandemic.

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "CamembertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 40005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e57237659da5b000e8f2f50557995684c3f1040bd1693df9890641c35ed495c
+size 467443364

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "name_or_path": "enhi",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}