Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +36 -0
- config.json +43 -0
- generation_config.json +10 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +57 -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 |
+
- MarketingHHM/autotrain-data-sumituptestv4
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 6.050113494900274
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Summarization
|
18 |
+
- Model ID: 60050134312
|
19 |
+
- CO2 Emissions (in grams): 6.0501
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 2.943
|
24 |
+
- Rouge1: 37.694
|
25 |
+
- Rouge2: 11.585
|
26 |
+
- RougeL: 23.248
|
27 |
+
- RougeLsum: 34.113
|
28 |
+
- Gen Len: 142.296
|
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/MarketingHHM/autotrain-sumituptestv4-60050134312
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"BigBirdPegasusForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"attention_type": "block_sparse",
|
10 |
+
"block_size": 64,
|
11 |
+
"bos_token_id": 2,
|
12 |
+
"classifier_dropout": 0.0,
|
13 |
+
"d_model": 1024,
|
14 |
+
"decoder_attention_heads": 16,
|
15 |
+
"decoder_ffn_dim": 4096,
|
16 |
+
"decoder_layerdrop": 0.0,
|
17 |
+
"decoder_layers": 16,
|
18 |
+
"decoder_start_token_id": 2,
|
19 |
+
"dropout": 0.1,
|
20 |
+
"encoder_attention_heads": 16,
|
21 |
+
"encoder_ffn_dim": 4096,
|
22 |
+
"encoder_layerdrop": 0.0,
|
23 |
+
"encoder_layers": 16,
|
24 |
+
"eos_token_id": 1,
|
25 |
+
"gradient_checkpointing": false,
|
26 |
+
"init_std": 0.02,
|
27 |
+
"is_encoder_decoder": true,
|
28 |
+
"length_penalty": 0.8,
|
29 |
+
"max_length": 256,
|
30 |
+
"max_position_embeddings": 4096,
|
31 |
+
"model_type": "bigbird_pegasus",
|
32 |
+
"num_beams": 5,
|
33 |
+
"num_hidden_layers": 16,
|
34 |
+
"num_random_blocks": 3,
|
35 |
+
"pad_token_id": 0,
|
36 |
+
"scale_embedding": true,
|
37 |
+
"tokenizer_class": "PegasusTokenizer",
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.28.1",
|
40 |
+
"use_bias": false,
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 96103
|
43 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 2,
|
3 |
+
"decoder_start_token_id": 2,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"length_penalty": 0.8,
|
6 |
+
"max_length": 256,
|
7 |
+
"num_beams": 5,
|
8 |
+
"pad_token_id": 0,
|
9 |
+
"transformers_version": "4.28.1"
|
10 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e722f126e7dc44b55b39c75e9721b522d26b1218c397f2b79897fd6beb2dab1
|
3 |
+
size 2308118957
|
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": "[CLS]",
|
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": "[SEP]",
|
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 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe1b40df7e8825709c0172639c47338a68d5622e9e3b6cc0fae516537cae738b
|
3 |
+
size 1915455
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b43e3e7aa75227a74faed9e38724c70874d7faca5d33f5558beb69e77667041
|
3 |
+
size 6579312
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [],
|
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": "[CLS]",
|
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 |
+
"mask_token": "[MASK]",
|
29 |
+
"mask_token_sent": null,
|
30 |
+
"model_max_length": 4096,
|
31 |
+
"offset": 0,
|
32 |
+
"pad_token": {
|
33 |
+
"__type": "AddedToken",
|
34 |
+
"content": "<pad>",
|
35 |
+
"lstrip": false,
|
36 |
+
"normalized": true,
|
37 |
+
"rstrip": false,
|
38 |
+
"single_word": false
|
39 |
+
},
|
40 |
+
"sep_token": {
|
41 |
+
"__type": "AddedToken",
|
42 |
+
"content": "[SEP]",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": true,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": false
|
47 |
+
},
|
48 |
+
"tokenizer_class": "PegasusTokenizer",
|
49 |
+
"unk_token": {
|
50 |
+
"__type": "AddedToken",
|
51 |
+
"content": "<unk>",
|
52 |
+
"lstrip": false,
|
53 |
+
"normalized": true,
|
54 |
+
"rstrip": false,
|
55 |
+
"single_word": false
|
56 |
+
}
|
57 |
+
}
|