Upload T5ForConditionalGeneration
Browse files- config.json +41 -11
- generation_config.json +2 -1
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,31 +1,61 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
-
"d_ff":
|
8 |
"d_kv": 64,
|
9 |
-
"d_model":
|
10 |
"decoder_start_token_id": 0,
|
11 |
-
"dense_act_fn": "
|
12 |
"dropout_rate": 0.1,
|
13 |
-
"eos_token_id":
|
14 |
-
"feed_forward_proj": "
|
15 |
"initializer_factor": 1.0,
|
16 |
"is_encoder_decoder": true,
|
17 |
-
"is_gated_act":
|
18 |
"layer_norm_epsilon": 1e-06,
|
|
|
19 |
"model_type": "t5",
|
20 |
"n_positions": 512,
|
21 |
-
"num_decoder_layers":
|
22 |
-
"num_heads":
|
23 |
-
"num_layers":
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
27 |
"relative_attention_num_buckets": 32,
|
28 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
"torch_dtype": "float32",
|
30 |
"transformers_version": "4.34.0",
|
31 |
"use_cache": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "zaaabik/t5-russian-summarization-detox-finetuning",
|
3 |
+
"_num_labels": 2,
|
4 |
"architectures": [
|
5 |
"T5ForConditionalGeneration"
|
6 |
],
|
7 |
"classifier_dropout": 0.0,
|
8 |
+
"d_ff": 3072,
|
9 |
"d_kv": 64,
|
10 |
+
"d_model": 768,
|
11 |
"decoder_start_token_id": 0,
|
12 |
+
"dense_act_fn": "relu",
|
13 |
"dropout_rate": 0.1,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"feed_forward_proj": "relu",
|
16 |
"initializer_factor": 1.0,
|
17 |
"is_encoder_decoder": true,
|
18 |
+
"is_gated_act": false,
|
19 |
"layer_norm_epsilon": 1e-06,
|
20 |
+
"max_length": 64,
|
21 |
"model_type": "t5",
|
22 |
"n_positions": 512,
|
23 |
+
"num_decoder_layers": 12,
|
24 |
+
"num_heads": 12,
|
25 |
+
"num_layers": 12,
|
26 |
"output_past": true,
|
27 |
"pad_token_id": 0,
|
28 |
"relative_attention_max_distance": 128,
|
29 |
"relative_attention_num_buckets": 32,
|
30 |
+
"task_specific_params": {
|
31 |
+
"summarization": {
|
32 |
+
"early_stopping": true,
|
33 |
+
"length_penalty": 2.0,
|
34 |
+
"max_length": 200,
|
35 |
+
"min_length": 30,
|
36 |
+
"no_repeat_ngram_size": 3,
|
37 |
+
"num_beams": 4,
|
38 |
+
"prefix": "summarize: "
|
39 |
+
},
|
40 |
+
"translation_en_to_de": {
|
41 |
+
"early_stopping": true,
|
42 |
+
"max_length": 300,
|
43 |
+
"num_beams": 4,
|
44 |
+
"prefix": "translate English to German: "
|
45 |
+
},
|
46 |
+
"translation_en_to_fr": {
|
47 |
+
"early_stopping": true,
|
48 |
+
"max_length": 300,
|
49 |
+
"num_beams": 4,
|
50 |
+
"prefix": "translate English to French: "
|
51 |
+
},
|
52 |
+
"translation_en_to_ro": {
|
53 |
+
"early_stopping": true,
|
54 |
+
"max_length": 300,
|
55 |
+
"num_beams": 4,
|
56 |
+
"prefix": "translate English to Romanian: "
|
57 |
+
}
|
58 |
+
},
|
59 |
"torch_dtype": "float32",
|
60 |
"transformers_version": "4.34.0",
|
61 |
"use_cache": false,
|
generation_config.json
CHANGED
@@ -1,7 +1,8 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"decoder_start_token_id": 0,
|
4 |
-
"eos_token_id":
|
|
|
5 |
"pad_token_id": 0,
|
6 |
"transformers_version": "4.34.0"
|
7 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 64,
|
6 |
"pad_token_id": 0,
|
7 |
"transformers_version": "4.34.0"
|
8 |
}
|
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 sha256:42760575190edbd92181b98540c177bed9ff40255f90031d61b712fa79c3e712
|
3 |
+
size 898832721
|