majedk01 commited on
Commit
ebb28be
1 Parent(s): 6063e94

Upload 11 files

Browse files
README.md CHANGED
@@ -1,12 +1,25 @@
1
  ---
2
- title: Text2Image
3
- emoji: 🖼
4
- colorFrom: purple
5
- colorTo: red
6
- sdk: gradio
7
- sdk_version: 4.26.0
8
- app_file: app.py
9
- pinned: false
10
  ---
11
 
12
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+ - translation
4
+ license: apache-2.0
 
 
 
 
 
5
  ---
6
 
7
+ ### opus-mt-ar-en
8
+
9
+ * source languages: ar
10
+ * target languages: en
11
+ * OPUS readme: [ar-en](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/ar-en/README.md)
12
+
13
+ * dataset: opus
14
+ * model: transformer-align
15
+ * pre-processing: normalization + SentencePiece
16
+ * download original weights: [opus-2019-12-18.zip](https://object.pouta.csc.fi/OPUS-MT-models/ar-en/opus-2019-12-18.zip)
17
+ * test set translations: [opus-2019-12-18.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/ar-en/opus-2019-12-18.test.txt)
18
+ * test set scores: [opus-2019-12-18.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/ar-en/opus-2019-12-18.eval.txt)
19
+
20
+ ## Benchmarks
21
+
22
+ | testset | BLEU | chr-F |
23
+ |-----------------------|-------|-------|
24
+ | Tatoeba.ar.en | 49.4 | 0.661 |
25
+
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/tmp/Helsinki-NLP/opus-mt-ar-en",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "swish",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "MarianMTModel"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bad_words_ids": [
13
+ [
14
+ 62833
15
+ ]
16
+ ],
17
+ "bos_token_id": 0,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 512,
21
+ "decoder_attention_heads": 8,
22
+ "decoder_ffn_dim": 2048,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 62833,
26
+ "decoder_vocab_size": 62834,
27
+ "dropout": 0.1,
28
+ "encoder_attention_heads": 8,
29
+ "encoder_ffn_dim": 2048,
30
+ "encoder_layerdrop": 0.0,
31
+ "encoder_layers": 6,
32
+ "eos_token_id": 0,
33
+ "forced_eos_token_id": 0,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1",
37
+ "2": "LABEL_2"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_2": 2
45
+ },
46
+ "max_length": 512,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "marian",
49
+ "normalize_before": false,
50
+ "normalize_embedding": false,
51
+ "num_beams": 4,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 62833,
54
+ "scale_embedding": true,
55
+ "share_encoder_decoder_embeddings": true,
56
+ "static_position_embeddings": true,
57
+ "transformers_version": "4.22.0.dev0",
58
+ "use_cache": true,
59
+ "vocab_size": 62834
60
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 62833
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 62833,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 62833,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.32.0.dev0"
16
+ }
gitattributes ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
2
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.h5 filter=lfs diff=lfs merge=lfs -text
5
+ *.tflite filter=lfs diff=lfs merge=lfs -text
6
+ *.tar.gz filter=lfs diff=lfs merge=lfs -text
7
+ *.ot filter=lfs diff=lfs merge=lfs -text
8
+ *.onnx filter=lfs diff=lfs merge=lfs -text
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e937a8dd33fa352c278029f190b1d077deb8c637152ff4039c202b72683935fb
3
+ size 307640325
rust_model.ot ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9435126415cf8a97b935d33223650582bac290792a0f400218b2fe37533db7f7
3
+ size 565035373
source.spm ADDED
Binary file (917 kB). View file
 
target.spm ADDED
Binary file (802 kB). View file
 
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64b57512977104ad6c4969f90763307c96ff0c7fcbbd9e5ef4ff5ee2dc4a066
3
+ size 308125248
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"target_lang": "en", "source_lang": "ar"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff