Hugging Face's logo

Jitin
/
romanized-malayalam

Fill-Mask
Transformers
PyTorch
JAX
roberta
Inference Endpoints
Model card Files Community
1
Jitin commited on
Commit
644b771
•
1 Parent(s): f18d8b9

First iteration of romanized malayalam model and tokenizer

Browse files
Files changed (10) hide show
  1. config.json +23 -0
  2. drive/My Drive/Colab Notebooks/malayalam/models/romanized_1M/config.json +23 -0
  3. drive/My Drive/Colab Notebooks/malayalam/models/romanized_1M/pytorch_model.bin +3 -0
  4. drive/My Drive/Colab Notebooks/malayalam/models/romanized_1M/training_args.bin +3 -0
  5. merges.txt +0 -0
  6. pytorch_model.bin +3 -0
  7. special_tokens_map.json +1 -0
  8. tokenizer_config.json +1 -0
  9. training_args.bin +3 -0
  10. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "type_vocab_size": 1,
22
+ "vocab_size": 52000
23
+ }
drive/My Drive/Colab Notebooks/malayalam/models/romanized_1M/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "type_vocab_size": 1,
22
+ "vocab_size": 52000
23
+ }
drive/My Drive/Colab Notebooks/malayalam/models/romanized_1M/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea4389f4ce49fa8434c39fc6050f33b393c5d5212e97826ea23eae73e8bbcb5
3
+ size 334066616
drive/My Drive/Colab Notebooks/malayalam/models/romanized_1M/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95891f342d458eedab89e4b54e3f9118b9551cf9a5a193db3d0a91034762f904
3
+ size 1839
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea4389f4ce49fa8434c39fc6050f33b393c5d5212e97826ea23eae73e8bbcb5
3
+ size 334066616
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "drive/My Drive/Colab Notebooks/malayalam/models/romanized_1M"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95891f342d458eedab89e4b54e3f9118b9551cf9a5a193db3d0a91034762f904
3
+ size 1839
vocab.json ADDED
The diff for this file is too large to render. See raw diff