model upload
Browse files- README.md +1 -1
- config.json +11 -10
- generation_config.json +9 -0
- pytorch_model.bin → model.safetensors +2 -2
README.md
CHANGED
@@ -33,7 +33,7 @@ length_penalty=1.5,
|
|
33 |
max_length=256,
|
34 |
min_length=12,
|
35 |
num_beams=6,
|
36 |
-
repetition_penalty=
|
37 |
)
|
38 |
|
39 |
# Decoding Text Ids
|
|
|
33 |
max_length=256,
|
34 |
min_length=12,
|
35 |
num_beams=6,
|
36 |
+
repetition_penalty=1.5,
|
37 |
)
|
38 |
|
39 |
# Decoding Text Ids
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"add_bias_logits": false,
|
@@ -9,7 +9,7 @@
|
|
9 |
],
|
10 |
"attention_dropout": 0.0,
|
11 |
"author": "EbanLee([email protected])",
|
12 |
-
"bos_token_id":
|
13 |
"classif_dropout": 0.1,
|
14 |
"classifier_dropout": 0.1,
|
15 |
"d_model": 768,
|
@@ -17,7 +17,7 @@
|
|
17 |
"decoder_ffn_dim": 3072,
|
18 |
"decoder_layerdrop": 0.0,
|
19 |
"decoder_layers": 6,
|
20 |
-
"decoder_start_token_id":
|
21 |
"do_blenderbot_90_layernorm": false,
|
22 |
"dropout": 0.1,
|
23 |
"encoder_attention_heads": 16,
|
@@ -27,7 +27,7 @@
|
|
27 |
"eos_token_id": 1,
|
28 |
"extra_pos_embeddings": 2,
|
29 |
"force_bos_token_to_be_generated": false,
|
30 |
-
"forced_eos_token_id":
|
31 |
"gradient_checkpointing": false,
|
32 |
"id2label": {
|
33 |
"0": "NEGATIVE",
|
@@ -48,17 +48,18 @@
|
|
48 |
"pad_token_id": 3,
|
49 |
"scale_embedding": false,
|
50 |
"static_position_embeddings": false,
|
|
|
|
|
|
|
|
|
|
|
51 |
"task_specific_params": {
|
52 |
"summarization": {
|
53 |
"length_penalty": 1.5,
|
54 |
"max_length": 256,
|
55 |
"min_length": 12,
|
56 |
"num_beams": 6,
|
57 |
-
"repetition_penalty":
|
58 |
}
|
59 |
-
}
|
60 |
-
"torch_dtype": "float32",
|
61 |
-
"transformers_version": "4.25.1",
|
62 |
-
"use_cache": true,
|
63 |
-
"vocab_size": 30000
|
64 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "kobart-summary-v2",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"add_bias_logits": false,
|
|
|
9 |
],
|
10 |
"attention_dropout": 0.0,
|
11 |
"author": "EbanLee([email protected])",
|
12 |
+
"bos_token_id": 1,
|
13 |
"classif_dropout": 0.1,
|
14 |
"classifier_dropout": 0.1,
|
15 |
"d_model": 768,
|
|
|
17 |
"decoder_ffn_dim": 3072,
|
18 |
"decoder_layerdrop": 0.0,
|
19 |
"decoder_layers": 6,
|
20 |
+
"decoder_start_token_id": 1,
|
21 |
"do_blenderbot_90_layernorm": false,
|
22 |
"dropout": 0.1,
|
23 |
"encoder_attention_heads": 16,
|
|
|
27 |
"eos_token_id": 1,
|
28 |
"extra_pos_embeddings": 2,
|
29 |
"force_bos_token_to_be_generated": false,
|
30 |
+
"forced_eos_token_id": 1,
|
31 |
"gradient_checkpointing": false,
|
32 |
"id2label": {
|
33 |
"0": "NEGATIVE",
|
|
|
48 |
"pad_token_id": 3,
|
49 |
"scale_embedding": false,
|
50 |
"static_position_embeddings": false,
|
51 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
52 |
+
"torch_dtype": "float32",
|
53 |
+
"transformers_version": "4.38.2",
|
54 |
+
"use_cache": true,
|
55 |
+
"vocab_size": 30000,
|
56 |
"task_specific_params": {
|
57 |
"summarization": {
|
58 |
"length_penalty": 1.5,
|
59 |
"max_length": 256,
|
60 |
"min_length": 12,
|
61 |
"num_beams": 6,
|
62 |
+
"repetition_penalty": 1.5
|
63 |
}
|
64 |
+
}
|
|
|
|
|
|
|
|
|
65 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"decoder_start_token_id": 1,
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"forced_eos_token_id": 1,
|
7 |
+
"pad_token_id": 3,
|
8 |
+
"transformers_version": "4.38.2"
|
9 |
+
}
|
pytorch_model.bin → model.safetensors
RENAMED
@@ -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 sha256:3eb2372526484e40732a6f421a8752ec2887ccc2eec8011c64ca8c6fb9dd4426
|
3 |
+
size 495589768
|