Commit
·
9055103
1
Parent(s):
f832947
Updated to Transformers v4
Browse files- config.json +11 -7
- pytorch_model.bin +2 -2
- requirements.txt +79 -0
- sparse_encoder.pk +0 -0
- sparse_weight.pt +2 -2
- special_tokens_map.json +1 -0
- flax_model.msgpack → tf_model.h5 +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
config.json
CHANGED
|
@@ -1,6 +1,10 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"attention_probs_dropout_prob": 0.1,
|
| 3 |
-
"
|
| 4 |
"hidden_act": "gelu",
|
| 5 |
"hidden_dropout_prob": 0.1,
|
| 6 |
"hidden_size": 768,
|
|
@@ -8,14 +12,14 @@
|
|
| 8 |
"intermediate_size": 3072,
|
| 9 |
"layer_norm_eps": 1e-12,
|
| 10 |
"max_position_embeddings": 512,
|
|
|
|
| 11 |
"num_attention_heads": 12,
|
| 12 |
"num_hidden_layers": 12,
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"torchscript": false,
|
| 18 |
"type_vocab_size": 2,
|
| 19 |
-
"
|
| 20 |
"vocab_size": 28996
|
| 21 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "BioSyn-master/Models/pybiobert2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
"hidden_act": "gelu",
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
"hidden_size": 768,
|
|
|
|
| 12 |
"intermediate_size": 3072,
|
| 13 |
"layer_norm_eps": 1e-12,
|
| 14 |
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
"num_attention_heads": 12,
|
| 17 |
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.11.3",
|
|
|
|
| 22 |
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
"vocab_size": 28996
|
| 25 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2153e33eb80408c25e619f214cf26e03ac55b25bc536490972934f02cd7a7498
|
| 3 |
+
size 433327607
|
requirements.txt
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
absl-py==1.0.0
|
| 2 |
+
astunparse==1.6.3
|
| 3 |
+
cached-property==1.5.2
|
| 4 |
+
cachetools==5.0.0
|
| 5 |
+
cchardet==2.1.7
|
| 6 |
+
certifi==2021.10.8
|
| 7 |
+
chardet==4.0.0
|
| 8 |
+
charset-normalizer==2.0.10
|
| 9 |
+
click==8.0.3
|
| 10 |
+
cycler==0.11.0
|
| 11 |
+
fastprogress==1.0.2
|
| 12 |
+
filelock==3.4.2
|
| 13 |
+
flatbuffers==2.0
|
| 14 |
+
fonttools==4.29.1
|
| 15 |
+
gast==0.5.3
|
| 16 |
+
google-auth==2.6.0
|
| 17 |
+
google-auth-oauthlib==0.4.6
|
| 18 |
+
google-pasta==0.2.0
|
| 19 |
+
grpcio==1.44.0
|
| 20 |
+
h5py==3.6.0
|
| 21 |
+
huggingface-hub==0.4.0
|
| 22 |
+
idna==3.3
|
| 23 |
+
importlib-metadata==4.10.0
|
| 24 |
+
jieba==0.42.1
|
| 25 |
+
keras==2.8.0
|
| 26 |
+
keras-bert==0.89.0
|
| 27 |
+
keras-embed-sim==0.10.0
|
| 28 |
+
keras-layer-normalization==0.16.0
|
| 29 |
+
keras-multi-head==0.29.0
|
| 30 |
+
keras-pos-embd==0.13.0
|
| 31 |
+
keras-position-wise-feed-forward==0.8.0
|
| 32 |
+
Keras-Preprocessing==1.1.2
|
| 33 |
+
keras-self-attention==0.51.0
|
| 34 |
+
keras-transformer==0.40.0
|
| 35 |
+
kiwisolver==1.3.2
|
| 36 |
+
ktrain==0.29.2
|
| 37 |
+
langdetect==1.0.9
|
| 38 |
+
libclang==13.0.0
|
| 39 |
+
Markdown==3.3.6
|
| 40 |
+
matplotlib==3.5.1
|
| 41 |
+
mkl-fft==1.3.1
|
| 42 |
+
mkl-service==2.4.0
|
| 43 |
+
oauthlib==3.2.0
|
| 44 |
+
opt-einsum==3.3.0
|
| 45 |
+
packaging==21.3
|
| 46 |
+
pandas==1.3.5
|
| 47 |
+
Pillow==9.0.1
|
| 48 |
+
protobuf==3.19.4
|
| 49 |
+
pyasn1==0.4.8
|
| 50 |
+
pyasn1-modules==0.2.8
|
| 51 |
+
pyparsing==3.0.6
|
| 52 |
+
python-dateutil==2.8.2
|
| 53 |
+
pytz==2021.3
|
| 54 |
+
PyYAML==6.0
|
| 55 |
+
regex==2021.11.10
|
| 56 |
+
requests==2.27.1
|
| 57 |
+
requests-oauthlib==1.3.1
|
| 58 |
+
rsa==4.8
|
| 59 |
+
sacremoses==0.0.47
|
| 60 |
+
scikit-learn==0.24.2
|
| 61 |
+
scipy==1.7.3
|
| 62 |
+
sentencepiece==0.1.96
|
| 63 |
+
seqeval==0.0.19
|
| 64 |
+
syntok==1.3.3
|
| 65 |
+
tensorboard==2.8.0
|
| 66 |
+
tensorboard-data-server==0.6.1
|
| 67 |
+
tensorboard-plugin-wit==1.8.1
|
| 68 |
+
tensorflow==2.8.0
|
| 69 |
+
tensorflow-io-gcs-filesystem==0.24.0
|
| 70 |
+
termcolor==1.1.0
|
| 71 |
+
tf-estimator-nightly==2.8.0.dev2021122109
|
| 72 |
+
tokenizers==0.10.3
|
| 73 |
+
torch==1.8.0
|
| 74 |
+
transformers==4.10.3
|
| 75 |
+
urllib3==1.26.8
|
| 76 |
+
Werkzeug==2.0.3
|
| 77 |
+
Whoosh==2.7.4
|
| 78 |
+
wrapt==1.13.3
|
| 79 |
+
zipp==3.7.0
|
sparse_encoder.pk
CHANGED
|
Binary files a/sparse_encoder.pk and b/sparse_encoder.pk differ
|
|
|
sparse_weight.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3be7cbe86ece8c01aac1a4935fe710d497d686a09723e55c3c060cc64800142
|
| 3 |
+
size 824
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
flax_model.msgpack → tf_model.h5
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e161c4daef5fd00ef17abccec00ea69b0f1f36967819fe543167fbe08202eb5
|
| 3 |
+
size 433508352
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "BioSyn-master/Models/pybiobert2", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|