bertoslav-limited
Browse files- config.json +22 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"max_position_embeddings": 512,
|
| 12 |
+
"model_type": "distilbert",
|
| 13 |
+
"n_heads": 12,
|
| 14 |
+
"n_layers": 6,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"qa_dropout": 0.1,
|
| 17 |
+
"seq_classif_dropout": 0.2,
|
| 18 |
+
"sinusoidal_pos_embds": false,
|
| 19 |
+
"torch_dtype": "float32",
|
| 20 |
+
"transformers_version": "4.13.0.dev0",
|
| 21 |
+
"vocab_size": 30000
|
| 22 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a44e2e440fc158b48bde012e8bcd7230782634ac0979545ea8716b089a5e6741
|
| 3 |
+
size 266377007
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"special_tokens_map_file": "/ext/ivan/c4/multilingual/tokenizer/trained_tokenizer/special_tokens_map.json", "name_or_path": "/ext/ivan/c4/multilingual/tokenizer/trained_tokenizer/", "tokenizer_class": "PreTrainedTokenizerFast"}
|