commit files to HF hub
Browse files- README.md +2 -2
- config.json +1 -1
- inference.py +2 -2
- openvino_model.bin +2 -2
- openvino_model.xml +0 -0
- special_tokens_map.json +42 -6
- tokenizer.json +6 -3
- tokenizer_config.json +51 -9
README.md
CHANGED
@@ -17,9 +17,9 @@ from transformers import AutoTokenizer, pipeline
|
|
17 |
# model_id should be set to either a local directory or a model available on the HuggingFace hub.
|
18 |
model_id = "helenai/Alireza1044-albert-base-v2-sst2-ov"
|
19 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
20 |
-
model = OVModelForSequenceClassification.from_pretrained(model_id)
|
21 |
pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
|
22 |
-
result = pipe("
|
23 |
print(result)
|
24 |
```
|
25 |
|
|
|
17 |
# model_id should be set to either a local directory or a model available on the HuggingFace hub.
|
18 |
model_id = "helenai/Alireza1044-albert-base-v2-sst2-ov"
|
19 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
20 |
+
model = OVModelForSequenceClassification.from_pretrained(model_id, revision=')
|
21 |
pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
|
22 |
+
result = pipe("hello world")
|
23 |
print(result)
|
24 |
```
|
25 |
|
config.json
CHANGED
@@ -29,7 +29,7 @@
|
|
29 |
"position_embedding_type": "absolute",
|
30 |
"problem_type": "single_label_classification",
|
31 |
"torch_dtype": "float32",
|
32 |
-
"transformers_version": "4.
|
33 |
"type_vocab_size": 2,
|
34 |
"vocab_size": 30000
|
35 |
}
|
|
|
29 |
"position_embedding_type": "absolute",
|
30 |
"problem_type": "single_label_classification",
|
31 |
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.40.2",
|
33 |
"type_vocab_size": 2,
|
34 |
"vocab_size": 30000
|
35 |
}
|
inference.py
CHANGED
@@ -4,7 +4,7 @@ from transformers import AutoTokenizer, pipeline
|
|
4 |
# model_id should be set to either a local directory or a model available on the HuggingFace hub.
|
5 |
model_id = "helenai/Alireza1044-albert-base-v2-sst2-ov"
|
6 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
7 |
-
model = OVModelForSequenceClassification.from_pretrained(model_id)
|
8 |
pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
|
9 |
-
result = pipe("
|
10 |
print(result)
|
|
|
4 |
# model_id should be set to either a local directory or a model available on the HuggingFace hub.
|
5 |
model_id = "helenai/Alireza1044-albert-base-v2-sst2-ov"
|
6 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
7 |
+
model = OVModelForSequenceClassification.from_pretrained(model_id, revision=')
|
8 |
pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
|
9 |
+
result = pipe("hello world")
|
10 |
print(result)
|
openvino_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 sha256:21592c3bde341ffa5ece610bf933beb54beb7927be0d1674c1c375bec6a19a5a
|
3 |
+
size 46744764
|
openvino_model.xml
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,25 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"mask_token": {
|
6 |
"content": "[MASK]",
|
7 |
"lstrip": true,
|
@@ -9,7 +27,25 @@
|
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
12 |
-
"pad_token":
|
13 |
-
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "[SEP]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"mask_token": {
|
24 |
"content": "[MASK]",
|
25 |
"lstrip": true,
|
|
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "[SEP]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
}
|
tokenizer.json
CHANGED
@@ -104,7 +104,8 @@
|
|
104 |
{
|
105 |
"type": "Metaspace",
|
106 |
"replacement": "▁",
|
107 |
-
"
|
|
|
108 |
}
|
109 |
]
|
110 |
},
|
@@ -186,7 +187,8 @@
|
|
186 |
"decoder": {
|
187 |
"type": "Metaspace",
|
188 |
"replacement": "▁",
|
189 |
-
"
|
|
|
190 |
},
|
191 |
"model": {
|
192 |
"type": "Unigram",
|
@@ -120192,6 +120194,7 @@
|
|
120192 |
"▁eloquent",
|
120193 |
-13.532299041748049
|
120194 |
]
|
120195 |
-
]
|
|
|
120196 |
}
|
120197 |
}
|
|
|
104 |
{
|
105 |
"type": "Metaspace",
|
106 |
"replacement": "▁",
|
107 |
+
"prepend_scheme": "always",
|
108 |
+
"split": true
|
109 |
}
|
110 |
]
|
111 |
},
|
|
|
187 |
"decoder": {
|
188 |
"type": "Metaspace",
|
189 |
"replacement": "▁",
|
190 |
+
"prepend_scheme": "always",
|
191 |
+
"split": true
|
192 |
},
|
193 |
"model": {
|
194 |
"type": "Unigram",
|
|
|
120194 |
"▁eloquent",
|
120195 |
-13.532299041748049
|
120196 |
]
|
120197 |
+
],
|
120198 |
+
"byte_fallback": false
|
120199 |
}
|
120200 |
}
|
tokenizer_config.json
CHANGED
@@ -1,22 +1,64 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "[CLS]",
|
|
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_lower_case": true,
|
5 |
"eos_token": "[SEP]",
|
6 |
"keep_accents": false,
|
7 |
-
"mask_token":
|
8 |
-
|
9 |
-
"content": "[MASK]",
|
10 |
-
"lstrip": true,
|
11 |
-
"normalized": true,
|
12 |
-
"rstrip": false,
|
13 |
-
"single_word": false
|
14 |
-
},
|
15 |
"model_max_length": 512,
|
|
|
16 |
"pad_token": "<pad>",
|
|
|
|
|
17 |
"remove_space": true,
|
18 |
"sep_token": "[SEP]",
|
19 |
-
"
|
20 |
"tokenizer_class": "AlbertTokenizer",
|
|
|
|
|
21 |
"unk_token": "<unk>"
|
22 |
}
|
|
|
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": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
"bos_token": "[CLS]",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "[CLS]",
|
47 |
"do_lower_case": true,
|
48 |
"eos_token": "[SEP]",
|
49 |
"keep_accents": false,
|
50 |
+
"mask_token": "[MASK]",
|
51 |
+
"max_length": 128,
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
"model_max_length": 512,
|
53 |
+
"pad_to_multiple_of": null,
|
54 |
"pad_token": "<pad>",
|
55 |
+
"pad_token_type_id": 0,
|
56 |
+
"padding_side": "right",
|
57 |
"remove_space": true,
|
58 |
"sep_token": "[SEP]",
|
59 |
+
"stride": 0,
|
60 |
"tokenizer_class": "AlbertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
"unk_token": "<unk>"
|
64 |
}
|