Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +36 -0
- config.json +59 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +21 -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 |
+
- abdalrahmanshahrour/autotrain-data-auto-arabic-summarization
|
11 |
+
co2_eq_emissions:
|
12 |
+
emissions: 23.934855677704917
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
- Problem type: Summarization
|
18 |
+
- Model ID: 2581378622
|
19 |
+
- CO2 Emissions (in grams): 23.9349
|
20 |
+
|
21 |
+
## Validation Metrics
|
22 |
+
|
23 |
+
- Loss: 0.829
|
24 |
+
- Rouge1: 1.132
|
25 |
+
- Rouge2: 0.127
|
26 |
+
- RougeL: 1.137
|
27 |
+
- RougeLsum: 1.129
|
28 |
+
- Gen Len: 19.774
|
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/abdalrahmanshahrour/autotrain-auto-arabic-summarization-2581378622
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": true,
|
7 |
+
"architectures": [
|
8 |
+
"MBartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"do_blenderbot_90_layernorm": false,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"early_stopping": true,
|
23 |
+
"encoder_attention_heads": 12,
|
24 |
+
"encoder_ffn_dim": 3072,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"extra_pos_embeddings": 2,
|
29 |
+
"force_bos_token_to_be_generated": false,
|
30 |
+
"forced_eos_token_id": 2,
|
31 |
+
"gradient_checkpointing": false,
|
32 |
+
"id2label": {
|
33 |
+
"0": "LABEL_0",
|
34 |
+
"1": "LABEL_1",
|
35 |
+
"2": "LABEL_2"
|
36 |
+
},
|
37 |
+
"init_std": 0.02,
|
38 |
+
"is_encoder_decoder": true,
|
39 |
+
"label2id": {
|
40 |
+
"LABEL_0": 0,
|
41 |
+
"LABEL_1": 1,
|
42 |
+
"LABEL_2": 2
|
43 |
+
},
|
44 |
+
"max_position_embeddings": 1024,
|
45 |
+
"model_type": "mbart",
|
46 |
+
"no_repeat_ngram_size": 3,
|
47 |
+
"normalize_before": true,
|
48 |
+
"normalize_embedding": true,
|
49 |
+
"num_beams": 4,
|
50 |
+
"num_hidden_layers": 6,
|
51 |
+
"pad_token_id": 1,
|
52 |
+
"scale_embedding": false,
|
53 |
+
"static_position_embeddings": false,
|
54 |
+
"tokenizer_class": "BarthezTokenizer",
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.25.1",
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 50002
|
59 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7397a91e0f2b6628f1a9fffddc1b07649f29decae03a45720687b27adc0cf05
|
3 |
+
size 557175853
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbb59d772bc9bb2da5dc4a73a00c61c0912c6d2596aad970fa2cd3d69898b245
|
3 |
+
size 1315170
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:587385b1d57e99a7a384d58f4d647ade3ded8ba6fe5c331913455c30f1e8ad8a
|
3 |
+
size 3781146
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"model_max_length": 1000000000000000019884624838656,
|
14 |
+
"name_or_path": "AutoTrain",
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"sp_model_kwargs": {},
|
18 |
+
"special_tokens_map_file": null,
|
19 |
+
"tokenizer_class": "BarthezTokenizer",
|
20 |
+
"unk_token": "<unk>"
|
21 |
+
}
|