Update README.md
Browse files
README.md
CHANGED
|
@@ -7,30 +7,7 @@ library_name: transformers
|
|
| 7 |
---
|
| 8 |
|
| 9 |
Roberta base model trained on Azerbaijani subset of OSCAR corpus.
|
| 10 |
-
|
| 11 |
-
attention_probs_dropout_prob:0.1
|
| 12 |
-
bos_token_id:0
|
| 13 |
-
classifier_dropout:null
|
| 14 |
-
eos_token_id:2
|
| 15 |
-
gradient_checkpointing:false
|
| 16 |
-
hidden_act:"gelu"
|
| 17 |
-
hidden_dropout_prob:0.1
|
| 18 |
-
hidden_size:768
|
| 19 |
-
initializer_range:0.02
|
| 20 |
-
intermediate_size:3072
|
| 21 |
-
layer_norm_eps:1e-12
|
| 22 |
-
max_position_embeddings:514
|
| 23 |
-
model_type:"roberta"
|
| 24 |
-
num_attention_heads:12
|
| 25 |
-
num_hidden_layers:6
|
| 26 |
-
pad_token_id:1
|
| 27 |
-
position_embedding_type:"absolute"
|
| 28 |
-
torch_dtype:"float32"
|
| 29 |
-
transformers_version:"4.10.0"
|
| 30 |
-
type_vocab_size:1
|
| 31 |
-
use_cache:true
|
| 32 |
-
vocab_size:52000
|
| 33 |
-
```
|
| 34 |
|
| 35 |
## Usage
|
| 36 |
```python
|
|
@@ -98,4 +75,30 @@ fill_mask("Mənə o yumşaq fransız bulkalarından <mask> çox ver")
|
|
| 98 |
'score': 0.011952652595937252,
|
| 99 |
'token': 524,
|
| 100 |
'token_str': ' çox'}]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
```
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
Roberta base model trained on Azerbaijani subset of OSCAR corpus.
|
| 10 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
## Usage
|
| 13 |
```python
|
|
|
|
| 75 |
'score': 0.011952652595937252,
|
| 76 |
'token': 524,
|
| 77 |
'token_str': ' çox'}]
|
| 78 |
+
```
|
| 79 |
+
|
| 80 |
+
## Config
|
| 81 |
+
```json
|
| 82 |
+
attention_probs_dropout_prob:0.1
|
| 83 |
+
bos_token_id:0
|
| 84 |
+
classifier_dropout:null
|
| 85 |
+
eos_token_id:2
|
| 86 |
+
gradient_checkpointing:false
|
| 87 |
+
hidden_act:"gelu"
|
| 88 |
+
hidden_dropout_prob:0.1
|
| 89 |
+
hidden_size:768
|
| 90 |
+
initializer_range:0.02
|
| 91 |
+
intermediate_size:3072
|
| 92 |
+
layer_norm_eps:1e-12
|
| 93 |
+
max_position_embeddings:514
|
| 94 |
+
model_type:"roberta"
|
| 95 |
+
num_attention_heads:12
|
| 96 |
+
num_hidden_layers:6
|
| 97 |
+
pad_token_id:1
|
| 98 |
+
position_embedding_type:"absolute"
|
| 99 |
+
torch_dtype:"float32"
|
| 100 |
+
transformers_version:"4.10.0"
|
| 101 |
+
type_vocab_size:1
|
| 102 |
+
use_cache:true
|
| 103 |
+
vocab_size:52000
|
| 104 |
```
|