Upload folder using huggingface_hub
Browse files- README.md +9 -0
- config.json +70 -0
- onnx/model.onnx +3 -0
- onnx/model_bnb4.onnx +3 -0
- onnx/model_fp16.onnx +3 -0
- onnx/model_int8.onnx +3 -0
- onnx/model_q4.onnx +3 -0
- onnx/model_q4f16.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- onnx/model_uint8.onnx +3 -0
- quantize_config.json +18 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +63 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers.js
|
| 3 |
+
base_model:
|
| 4 |
+
- hatmimoha/arabic-ner
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# arabic-ner (ONNX)
|
| 8 |
+
|
| 9 |
+
This is an ONNX version of [hatmimoha/arabic-ner](https://huggingface.co/hatmimoha/arabic-ner). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
|
config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"_name_or_path": "hatmimoha/arabic-ner",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "B-COMPETITION",
|
| 15 |
+
"1": "B-DATE",
|
| 16 |
+
"2": "B-DISEASE",
|
| 17 |
+
"3": "B-EVENT",
|
| 18 |
+
"4": "B-LOCATION",
|
| 19 |
+
"5": "B-ORGANIZATION",
|
| 20 |
+
"6": "B-PERSON",
|
| 21 |
+
"7": "B-PRICE",
|
| 22 |
+
"8": "B-PRODUCT",
|
| 23 |
+
"9": "I-COMPETITION",
|
| 24 |
+
"10": "I-DATE",
|
| 25 |
+
"11": "I-DISEASE",
|
| 26 |
+
"12": "I-EVENT",
|
| 27 |
+
"13": "I-LOCATION",
|
| 28 |
+
"14": "I-ORGANIZATION",
|
| 29 |
+
"15": "I-PERSON",
|
| 30 |
+
"16": "I-PRICE",
|
| 31 |
+
"17": "I-PRODUCT",
|
| 32 |
+
"18": "O"
|
| 33 |
+
},
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 3072,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"B-COMPETITION": 0,
|
| 38 |
+
"B-DATE": 1,
|
| 39 |
+
"B-DISEASE": 2,
|
| 40 |
+
"B-EVENT": 3,
|
| 41 |
+
"B-LOCATION": 4,
|
| 42 |
+
"B-ORGANIZATION": 5,
|
| 43 |
+
"B-PERSON": 6,
|
| 44 |
+
"B-PRICE": 7,
|
| 45 |
+
"B-PRODUCT": 8,
|
| 46 |
+
"I-COMPETITION": 9,
|
| 47 |
+
"I-DATE": 10,
|
| 48 |
+
"I-DISEASE": 11,
|
| 49 |
+
"I-EVENT": 12,
|
| 50 |
+
"I-LOCATION": 13,
|
| 51 |
+
"I-ORGANIZATION": 14,
|
| 52 |
+
"I-PERSON": 15,
|
| 53 |
+
"I-PRICE": 16,
|
| 54 |
+
"I-PRODUCT": 17,
|
| 55 |
+
"O": 18
|
| 56 |
+
},
|
| 57 |
+
"layer_norm_eps": 1e-12,
|
| 58 |
+
"max_position_embeddings": 512,
|
| 59 |
+
"model_type": "bert",
|
| 60 |
+
"num_attention_heads": 12,
|
| 61 |
+
"num_hidden_layers": 12,
|
| 62 |
+
"output_past": true,
|
| 63 |
+
"pad_token_id": 0,
|
| 64 |
+
"position_embedding_type": "absolute",
|
| 65 |
+
"torch_dtype": "float32",
|
| 66 |
+
"transformers_version": "4.49.0",
|
| 67 |
+
"type_vocab_size": 2,
|
| 68 |
+
"use_cache": true,
|
| 69 |
+
"vocab_size": 32000
|
| 70 |
+
}
|
onnx/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a1b729cb666278b03606c42e3fbf12db94aff2a35fd91f7b88d069b27563cb4
|
| 3 |
+
size 440473246
|
onnx/model_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7a43d95641aad4f4b5d100bb8ccddf4a214d9080dd1e7e717e0be546ca9dcbc
|
| 3 |
+
size 148471560
|
onnx/model_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:483251038ce1c86c0e88cfedd4953915bb652497c358bed7889d75734ec64dff
|
| 3 |
+
size 220390802
|
onnx/model_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e1c68e5d812835b8d0770e0693764d8d96276971585d77e9b59c97c5217ded9
|
| 3 |
+
size 111222949
|
onnx/model_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4d2fd79a97e53d8679635ac7105cc0ea6b85af7001a19469784793b92b5c7cd
|
| 3 |
+
size 153780352
|
onnx/model_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:376e45302663fc19ea952f292b8a0193a0017fe8bd53328817e1d08239abb2aa
|
| 3 |
+
size 98287173
|
onnx/model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e1c68e5d812835b8d0770e0693764d8d96276971585d77e9b59c97c5217ded9
|
| 3 |
+
size 111222949
|
onnx/model_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bd0154ef0250dd92a4146dc0a099f5142cd0676f0817cff588d15f0d9fbfd68
|
| 3 |
+
size 111222949
|
quantize_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"modes": [
|
| 3 |
+
"fp16",
|
| 4 |
+
"q8",
|
| 5 |
+
"int8",
|
| 6 |
+
"uint8",
|
| 7 |
+
"q4",
|
| 8 |
+
"q4f16",
|
| 9 |
+
"bnb4"
|
| 10 |
+
],
|
| 11 |
+
"per_channel": true,
|
| 12 |
+
"reduce_range": true,
|
| 13 |
+
"block_size": null,
|
| 14 |
+
"is_symmetric": true,
|
| 15 |
+
"accuracy_level": null,
|
| 16 |
+
"quant_type": 1,
|
| 17 |
+
"op_block_list": null
|
| 18 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"full_tokenizer_file": null,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"max_length": 512,
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"never_split": null,
|
| 54 |
+
"pad_token": "[PAD]",
|
| 55 |
+
"sep_token": "[SEP]",
|
| 56 |
+
"stride": 0,
|
| 57 |
+
"strip_accents": null,
|
| 58 |
+
"tokenize_chinese_chars": true,
|
| 59 |
+
"tokenizer_class": "BertTokenizer",
|
| 60 |
+
"truncation_side": "right",
|
| 61 |
+
"truncation_strategy": "longest_first",
|
| 62 |
+
"unk_token": "[UNK]"
|
| 63 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|