upload model
Browse files- added_tokens.json +1 -0
- language_model.bin +3 -0
- language_model_config.json +28 -0
- merges.txt +0 -0
- prediction_head_0.bin +3 -0
- prediction_head_0_config.json +1 -0
- processor_config.json +1 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"[QSPAN_END]": 50266, "[QSPAN_START]": 50265}
|
language_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:527128df5cee55eb0e79ea07fb58d5193fbd1720982458efdee4953120c4d205
|
3 |
+
size 498670065
|
language_model_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"language": "english",
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"name": "Roberta",
|
20 |
+
"num_attention_heads": 12,
|
21 |
+
"num_hidden_layers": 12,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "absolute",
|
24 |
+
"transformers_version": "4.13.0",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 50267
|
28 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
prediction_head_0.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:802ac11d6ed2f7416035e33b77c1e7ce2cfe1742ea4880a7693881a25bf3bba0
|
3 |
+
size 3157636
|
prediction_head_0_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"training": false, "layer_dims": [768, 2], "num_labels": 2, "ph_output_type": "per_token_squad", "model_type": "span_classification", "task_name": "question_answering", "no_ans_boost": 0.0, "context_window_size": 150, "n_best": 4, "n_best_per_sample": 1, "duplicate_filtering": 0, "use_confidence_scores_for_ranking": false, "label_tensor_name": "question_answering_label_ids", "label_list": ["start_token", "end_token"], "metric": "squad", "name": "KentonQuestionAnsweringHead"}
|
processor_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"add_special_tokens": true, "baskets": [], "batch_size": 12, "data_dir": "data/resources/squad/context", "dev_filename": "Dev_squad_format_1pos_23neg.json", "dev_split": 0, "doc_stride": 128, "max_answers": 6, "max_query_length": 64, "max_seq_len": 256, "multithreading_rust": true, "num_negatives": 23, "num_positives": 1, "ph_output_type": "per_token_squad", "proxies": null, "sp_toks_end": 1, "sp_toks_mid": 2, "sp_toks_start": 1, "tasks": {"question_answering": {"label_list": ["start_token", "end_token"], "metric": "squad", "label_tensor_name": "question_answering_label_ids", "label_name": "question_answering_label", "label_column_name": null, "text_column_name": null, "task_type": null}}, "test_filename": null, "train_filename": "Train_squad_format_1pos_23neg.json", "tokenizer": "RobertaTokenizerFast", "processor": "CoreSearchSquadProcessor"}
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["[QSPAN_START]", "[QSPAN_END]"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "prediction_head_str": "kenton", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|