Model save
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +35 -0
- generation_config.json +10 -0
- pytorch_model.bin +3 -0
- runs/Apr19_18-02-25_45cf9f09b7cf/1713549817.3871398/events.out.tfevents.1713549817.45cf9f09b7cf.751.1 +3 -0
- runs/Apr19_18-02-25_45cf9f09b7cf/events.out.tfevents.1713549817.45cf9f09b7cf.751.0 +3 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +11 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ahmed0189/mT5-Arabic-text-summarization",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 1024,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 512,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "gated-gelu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": true,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"length_penalty": 0.6,
|
19 |
+
"max_length": 128,
|
20 |
+
"model_type": "mt5",
|
21 |
+
"no_repeat_ngram_size": 2,
|
22 |
+
"num_beams": 15,
|
23 |
+
"num_decoder_layers": 8,
|
24 |
+
"num_heads": 6,
|
25 |
+
"num_layers": 8,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"relative_attention_max_distance": 128,
|
28 |
+
"relative_attention_num_buckets": 32,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"tokenizer_class": "T5Tokenizer",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.28.0",
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 250112
|
35 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"length_penalty": 0.6,
|
5 |
+
"max_length": 128,
|
6 |
+
"no_repeat_ngram_size": 2,
|
7 |
+
"num_beams": 15,
|
8 |
+
"pad_token_id": 0,
|
9 |
+
"transformers_version": "4.28.0"
|
10 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fd2285d3b22426d58bfd64500a88125444892ef8fe2a2ae02a224b954667feb
|
3 |
+
size 1200772930
|
runs/Apr19_18-02-25_45cf9f09b7cf/1713549817.3871398/events.out.tfevents.1713549817.45cf9f09b7cf.751.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da2c820255af34cb880431fd53a215521f0ae71e7c22640ee09bba8b9b77cff5
|
3 |
+
size 6137
|
runs/Apr19_18-02-25_45cf9f09b7cf/events.out.tfevents.1713549817.45cf9f09b7cf.751.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7812a5272713dc4d8d159e52506c2e885c2fa31263a37527a0af5a12a112bb57
|
3 |
+
size 5248
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2da8fdef37429469238f64f0b3ae7eee87b491b3a03d1c04ab052b8a3702b332
|
3 |
+
size 16315219
|
tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"extra_ids": 0,
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"sp_model_kwargs": {},
|
9 |
+
"tokenizer_class": "T5Tokenizer",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c56b3b57cb7deb031a457ec972c2d56c0b34460ba1064658defc9527823b5c23
|
3 |
+
size 4152
|