Training in progress step 15000
Browse files- added_tokens.json +21 -0
- config.json +44 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"☀": 50276,
|
| 3 |
+
"✨": 50271,
|
| 4 |
+
"🇺🇸": 50275,
|
| 5 |
+
"🎄": 50281,
|
| 6 |
+
"💕": 50267,
|
| 7 |
+
"💙": 50272,
|
| 8 |
+
"💜": 50277,
|
| 9 |
+
"💯": 50279,
|
| 10 |
+
"📷": 50274,
|
| 11 |
+
"📸": 50282,
|
| 12 |
+
"🔥": 50268,
|
| 13 |
+
"😁": 50280,
|
| 14 |
+
"😂": 50266,
|
| 15 |
+
"😉": 50278,
|
| 16 |
+
"😊": 50269,
|
| 17 |
+
"😍": 50265,
|
| 18 |
+
"😎": 50270,
|
| 19 |
+
"😘": 50273,
|
| 20 |
+
"😜": 50283
|
| 21 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BartForConditionalGeneration"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": 0.0,
|
| 10 |
+
"d_model": 1024,
|
| 11 |
+
"decoder_attention_heads": 16,
|
| 12 |
+
"decoder_ffn_dim": 4096,
|
| 13 |
+
"decoder_layerdrop": 0.0,
|
| 14 |
+
"decoder_layers": 12,
|
| 15 |
+
"decoder_start_token_id": 2,
|
| 16 |
+
"dropout": 0.1,
|
| 17 |
+
"encoder_attention_heads": 16,
|
| 18 |
+
"encoder_ffn_dim": 4096,
|
| 19 |
+
"encoder_layerdrop": 0.0,
|
| 20 |
+
"encoder_layers": 12,
|
| 21 |
+
"eos_token_id": 2,
|
| 22 |
+
"forced_eos_token_id": 2,
|
| 23 |
+
"id2label": {
|
| 24 |
+
"0": "LABEL_0",
|
| 25 |
+
"1": "LABEL_1",
|
| 26 |
+
"2": "LABEL_2"
|
| 27 |
+
},
|
| 28 |
+
"init_std": 0.02,
|
| 29 |
+
"is_encoder_decoder": true,
|
| 30 |
+
"label2id": {
|
| 31 |
+
"LABEL_0": 0,
|
| 32 |
+
"LABEL_1": 1,
|
| 33 |
+
"LABEL_2": 2
|
| 34 |
+
},
|
| 35 |
+
"max_position_embeddings": 1024,
|
| 36 |
+
"model_type": "bart",
|
| 37 |
+
"num_hidden_layers": 12,
|
| 38 |
+
"pad_token_id": 1,
|
| 39 |
+
"scale_embedding": false,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.21.1",
|
| 42 |
+
"use_cache": true,
|
| 43 |
+
"vocab_size": 50284
|
| 44 |
+
}
|
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 sha256:512ebde81e3e448a22ef594456c4d37ef63d07004de7aeeee468238b08e8283c
|
| 3 |
+
size 1625615681
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 1024,
|
| 9 |
+
"name_or_path": "facebook/bart-large-cnn",
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"special_tokens_map_file": null,
|
| 13 |
+
"tokenizer_class": "BartTokenizer",
|
| 14 |
+
"trim_offsets": true,
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|