Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +36 -0
- config.json +68 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +64 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -32,3 +32,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- summarization
|
5 |
+
language:
|
6 |
+
- unk
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain 🤗"
|
9 |
+
datasets:
|
10 |
+
- Udit191/autotrain-data-summarization-led_base
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 20.77094576685784
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Summarization
|
18 |
+
- Model ID: 56565131119
|
19 |
+
- CO2 Emissions (in grams): 20.7709
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 2.506
|
24 |
+
- Rouge1: 48.873
|
25 |
+
- Rouge2: 20.930
|
26 |
+
- RougeL: 26.731
|
27 |
+
- RougeLsum: 43.847
|
28 |
+
- Gen Len: 230.300
|
29 |
+
|
30 |
+
## Usage
|
31 |
+
|
32 |
+
You can use cURL to access this model:
|
33 |
+
|
34 |
+
```
|
35 |
+
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/Udit191/autotrain-summarization-led_base-56565131119
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"architectures": [
|
7 |
+
"LEDForConditionalGeneration"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"attention_window": [
|
11 |
+
1024,
|
12 |
+
1024,
|
13 |
+
1024,
|
14 |
+
1024,
|
15 |
+
1024,
|
16 |
+
1024,
|
17 |
+
1024,
|
18 |
+
1024,
|
19 |
+
1024,
|
20 |
+
1024,
|
21 |
+
1024,
|
22 |
+
1024
|
23 |
+
],
|
24 |
+
"bos_token_id": 0,
|
25 |
+
"classif_dropout": 0.0,
|
26 |
+
"classifier_dropout": 0.0,
|
27 |
+
"d_model": 1024,
|
28 |
+
"decoder_attention_heads": 16,
|
29 |
+
"decoder_ffn_dim": 4096,
|
30 |
+
"decoder_layerdrop": 0.0,
|
31 |
+
"decoder_layers": 12,
|
32 |
+
"decoder_start_token_id": 2,
|
33 |
+
"dropout": 0.1,
|
34 |
+
"early_stopping": true,
|
35 |
+
"encoder_attention_heads": 16,
|
36 |
+
"encoder_ffn_dim": 4096,
|
37 |
+
"encoder_layerdrop": 0.0,
|
38 |
+
"encoder_layers": 12,
|
39 |
+
"eos_token_id": 2,
|
40 |
+
"id2label": {
|
41 |
+
"0": "LABEL_0",
|
42 |
+
"1": "LABEL_1",
|
43 |
+
"2": "LABEL_2"
|
44 |
+
},
|
45 |
+
"init_std": 0.02,
|
46 |
+
"is_encoder_decoder": true,
|
47 |
+
"label2id": {
|
48 |
+
"LABEL_0": 0,
|
49 |
+
"LABEL_1": 1,
|
50 |
+
"LABEL_2": 2
|
51 |
+
},
|
52 |
+
"length_penalty": 2.0,
|
53 |
+
"max_decoder_position_embeddings": 1024,
|
54 |
+
"max_encoder_position_embeddings": 16384,
|
55 |
+
"max_length": 512,
|
56 |
+
"min_length": 100,
|
57 |
+
"model_type": "led",
|
58 |
+
"no_repeat_ngram_size": 3,
|
59 |
+
"num_beams": 4,
|
60 |
+
"num_hidden_layers": 12,
|
61 |
+
"output_past": false,
|
62 |
+
"pad_token_id": 1,
|
63 |
+
"prefix": " ",
|
64 |
+
"torch_dtype": "float32",
|
65 |
+
"transformers_version": "4.28.1",
|
66 |
+
"use_cache": false,
|
67 |
+
"vocab_size": 50265
|
68 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"decoder_start_token_id": 2,
|
4 |
+
"early_stopping": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"length_penalty": 2.0,
|
7 |
+
"max_length": 512,
|
8 |
+
"min_length": 100,
|
9 |
+
"no_repeat_ngram_size": 3,
|
10 |
+
"num_beams": 4,
|
11 |
+
"pad_token_id": 1,
|
12 |
+
"transformers_version": "4.28.1",
|
13 |
+
"use_cache": false
|
14 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4aac1f125a08cc6b4748a80120e72808c0be10f9975730303d7419d920bfd6c
|
3 |
+
size 1839608749
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29308def5aab464aa945ace46cc6008c60986e85d188b5b395da321e372ea898
|
3 |
+
size 2108712
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
+
"cls_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"eos_token": {
|
21 |
+
"__type": "AddedToken",
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"errors": "replace",
|
29 |
+
"mask_token": {
|
30 |
+
"__type": "AddedToken",
|
31 |
+
"content": "<mask>",
|
32 |
+
"lstrip": true,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"model_max_length": 16384,
|
38 |
+
"pad_token": {
|
39 |
+
"__type": "AddedToken",
|
40 |
+
"content": "<pad>",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": true,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"sep_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "</s>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"tokenizer_class": "LEDTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": {
|
57 |
+
"__type": "AddedToken",
|
58 |
+
"content": "<unk>",
|
59 |
+
"lstrip": false,
|
60 |
+
"normalized": true,
|
61 |
+
"rstrip": false,
|
62 |
+
"single_word": false
|
63 |
+
}
|
64 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|