basic training
Browse files- config.json +7 -6
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/content/drive/MyDrive/
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
6 |
"d_ff": 2048,
|
7 |
"d_kv": 64,
|
8 |
"d_model": 512,
|
@@ -13,19 +14,19 @@
|
|
13 |
"feed_forward_proj": "relu",
|
14 |
"initializer_factor": 1.0,
|
15 |
"is_encoder_decoder": true,
|
16 |
-
"is_gated_act":
|
17 |
"layer_norm_epsilon": 1e-06,
|
18 |
"model_type": "t5",
|
19 |
-
"
|
20 |
-
"num_decoder_layers": 20,
|
21 |
"num_heads": 8,
|
22 |
-
"num_layers":
|
23 |
"output_past": true,
|
24 |
"pad_token_id": 0,
|
25 |
"relative_attention_max_distance": 128,
|
26 |
"relative_attention_num_buckets": 32,
|
|
|
27 |
"torch_dtype": "float32",
|
28 |
"transformers_version": "4.26.1",
|
29 |
"use_cache": true,
|
30 |
-
"vocab_size":
|
31 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/content/drive/MyDrive/news/model2",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
"d_ff": 2048,
|
8 |
"d_kv": 64,
|
9 |
"d_model": 512,
|
|
|
14 |
"feed_forward_proj": "relu",
|
15 |
"initializer_factor": 1.0,
|
16 |
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
+
"num_decoder_layers": 16,
|
|
|
21 |
"num_heads": 8,
|
22 |
+
"num_layers": 16,
|
23 |
"output_past": true,
|
24 |
"pad_token_id": 0,
|
25 |
"relative_attention_max_distance": 128,
|
26 |
"relative_attention_num_buckets": 32,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
"torch_dtype": "float32",
|
29 |
"transformers_version": "4.26.1",
|
30 |
"use_cache": true,
|
31 |
+
"vocab_size": 32128
|
32 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06d6968e89d7cdf95af815e8dfb947c49865de30e830d504becbd207f20d4939
|
3 |
+
size 735875429
|