Narsil HF staff commited on
Commit
07a3942
1 Parent(s): f33e3f9

Small2 but sharded.

Browse files

Created to test safetensors conversion.

README.md ADDED
@@ -0,0 +1 @@
 
 
1
+ Small change. again. again ? again.
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Narsil/small2",
3
+ "_num_labels": 9,
4
+ "architectures": ["BertForTokenClassification"],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 2,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-MISC",
15
+ "2": "I-MISC",
16
+ "3": "B-PER",
17
+ "4": "I-PER",
18
+ "5": "B-ORG",
19
+ "6": "I-ORG",
20
+ "7": "B-LOC",
21
+ "8": "I-LOC"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 4,
25
+ "label2id": {
26
+ "B-LOC": 7,
27
+ "B-MISC": 1,
28
+ "B-ORG": 5,
29
+ "B-PER": 3,
30
+ "I-LOC": 8,
31
+ "I-MISC": 2,
32
+ "I-ORG": 6,
33
+ "I-PER": 4,
34
+ "O": 0
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 2,
40
+ "num_hidden_layers": 2,
41
+ "pad_token_id": 0,
42
+ "pooler_fc_size": 768,
43
+ "pooler_num_attention_heads": 12,
44
+ "pooler_num_fc_layers": 3,
45
+ "pooler_size_per_head": 128,
46
+ "pooler_type": "first_token_transform",
47
+ "position_embedding_type": "absolute",
48
+ "transformers_version": "4.10.0.dev0",
49
+ "type_vocab_size": 2,
50
+ "use_cache": true,
51
+ "vocab_size": 28996
52
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f87650c29f497c39f9265f3f8d5cbff82d350d656f17f84211f604773569eb3f
3
+ size 4907
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2c2f5f27c0ef9e57571711be399b4f6db326d559b66102a5fa9276affafb1e
3
+ size 232747
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350be52b37c1248f4df7fc72adf5105202166780689215c2ff1269a33f2ed5ff
3
+ size 15795
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 240732
4
+ },
5
+ "weight_map": {
6
+ "bert.embeddings.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
7
+ "bert.embeddings.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
8
+ "bert.embeddings.position_embeddings.weight": "pytorch_model-00003-of-00003.bin",
9
+ "bert.embeddings.position_ids": "pytorch_model-00001-of-00003.bin",
10
+ "bert.embeddings.token_type_embeddings.weight": "pytorch_model-00003-of-00003.bin",
11
+ "bert.embeddings.word_embeddings.weight": "pytorch_model-00002-of-00003.bin",
12
+ "bert.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
13
+ "bert.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
14
+ "bert.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
15
+ "bert.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
16
+ "bert.encoder.layer.0.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
17
+ "bert.encoder.layer.0.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
18
+ "bert.encoder.layer.0.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
19
+ "bert.encoder.layer.0.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
20
+ "bert.encoder.layer.0.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
21
+ "bert.encoder.layer.0.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
22
+ "bert.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
23
+ "bert.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
24
+ "bert.encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
25
+ "bert.encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
26
+ "bert.encoder.layer.0.output.dense.bias": "pytorch_model-00003-of-00003.bin",
27
+ "bert.encoder.layer.0.output.dense.weight": "pytorch_model-00003-of-00003.bin",
28
+ "bert.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
29
+ "bert.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
30
+ "bert.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
31
+ "bert.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
32
+ "bert.encoder.layer.1.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
33
+ "bert.encoder.layer.1.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
34
+ "bert.encoder.layer.1.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
35
+ "bert.encoder.layer.1.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
36
+ "bert.encoder.layer.1.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
37
+ "bert.encoder.layer.1.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
38
+ "bert.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
39
+ "bert.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
40
+ "bert.encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
41
+ "bert.encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
42
+ "bert.encoder.layer.1.output.dense.bias": "pytorch_model-00003-of-00003.bin",
43
+ "bert.encoder.layer.1.output.dense.weight": "pytorch_model-00003-of-00003.bin",
44
+ "classifier.bias": "pytorch_model-00003-of-00003.bin",
45
+ "classifier.weight": "pytorch_model-00003-of-00003.bin"
46
+ }
47
+ }
roberta.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28422e5654b34d4d92f8675c7b563e01992322451c74cefec9137084ac797766
3
+ size 301400
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "max_len": 512, "special_tokens_map_file": "/home/nicolas/.cache/torch/transformers/7ed0658a09e4f9689057c83f8b734d0e8d739f73461c7b7d1bc403aa451e304b.275045728fbf41c11d3dae08b8742c054377e18d92cc7b72b6351152a99b64e4", "tokenizer_file": null}
unigram.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e6c5a850287ee371b9c2c74ba1c9b10a85ce0436c0e53685903caa635dd2aa3
3
+ size 146491
vocab.txt ADDED
The diff for this file is too large to render. See raw diff