Model save
Browse files- best_eval_f1/added_tokens.json +3 -0
- best_eval_f1/bpe.codes +0 -0
- best_eval_f1/config.json +43 -0
- best_eval_f1/pytorch_model.bin +3 -0
- best_eval_f1/special_tokens_map.json +9 -0
- best_eval_f1/tokenizer_config.json +13 -0
- best_eval_f1/training_args.bin +3 -0
- best_eval_f1/vocab.txt +0 -0
best_eval_f1/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 64000
|
| 3 |
+
}
|
best_eval_f1/bpe.codes
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
best_eval_f1/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "vinai/phobert-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "B-RM",
|
| 16 |
+
"1": "I-RM",
|
| 17 |
+
"2": "B-IM",
|
| 18 |
+
"3": "I-IM",
|
| 19 |
+
"4": "O"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 4096,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"B-IM": 2,
|
| 25 |
+
"B-RM": 0,
|
| 26 |
+
"I-IM": 3,
|
| 27 |
+
"I-RM": 1,
|
| 28 |
+
"O": 4
|
| 29 |
+
},
|
| 30 |
+
"layer_norm_eps": 1e-05,
|
| 31 |
+
"max_position_embeddings": 258,
|
| 32 |
+
"model_type": "roberta",
|
| 33 |
+
"num_attention_heads": 16,
|
| 34 |
+
"num_hidden_layers": 24,
|
| 35 |
+
"pad_token_id": 1,
|
| 36 |
+
"position_embedding_type": "absolute",
|
| 37 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.27.4",
|
| 40 |
+
"type_vocab_size": 1,
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 64001
|
| 43 |
+
}
|
best_eval_f1/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9e487085d37325d674c36aae8a2c81b57e86a1aa26a54805429e398c3779bb8
|
| 3 |
+
size 1472612461
|
best_eval_f1/special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": "<mask>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "</s>",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
best_eval_f1/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_special_tokens": true,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"mask_token": "<mask>",
|
| 7 |
+
"model_max_length": 256,
|
| 8 |
+
"pad_token": "<pad>",
|
| 9 |
+
"sep_token": "</s>",
|
| 10 |
+
"special_tokens_map_file": null,
|
| 11 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 12 |
+
"unk_token": "<unk>"
|
| 13 |
+
}
|
best_eval_f1/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60afcee1c3800d56a5f8799f33f598a5858800c6a93198bde0f68de3eee494d3
|
| 3 |
+
size 3579
|
best_eval_f1/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|