Upload MBartForConditionalGeneration
Browse files- config.json +59 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/krotima1/projects/python/git_krotima1/output/trainModel/BRIO/BRIO_mbart_alignscorecs_8_8filtered_sort_TRouge_FRougeAlignscore_nogold=True_margin001_ctr100/checkpoint-10000",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": true,
|
8 |
+
"architectures": [
|
9 |
+
"MBartForConditionalGeneration"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.0,
|
14 |
+
"classifier_dropout": 0.0,
|
15 |
+
"d_model": 1024,
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 4096,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 12,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"encoder_attention_heads": 16,
|
22 |
+
"encoder_ffn_dim": 4096,
|
23 |
+
"encoder_layerdrop": 0.0,
|
24 |
+
"encoder_layers": 12,
|
25 |
+
"eos_token_id": 2,
|
26 |
+
"forced_eos_token_id": 2,
|
27 |
+
"id2label": {
|
28 |
+
"0": "LABEL_0",
|
29 |
+
"1": "LABEL_1",
|
30 |
+
"2": "LABEL_2"
|
31 |
+
},
|
32 |
+
"init_std": 0.02,
|
33 |
+
"is_encoder_decoder": true,
|
34 |
+
"label2id": {
|
35 |
+
"LABEL_0": 0,
|
36 |
+
"LABEL_1": 1,
|
37 |
+
"LABEL_2": 2
|
38 |
+
},
|
39 |
+
"max_length": 1024,
|
40 |
+
"max_position_embeddings": 1024,
|
41 |
+
"model_type": "mbart",
|
42 |
+
"normalize_before": true,
|
43 |
+
"normalize_embedding": true,
|
44 |
+
"num_beams": 5,
|
45 |
+
"num_hidden_layers": 12,
|
46 |
+
"output_past": true,
|
47 |
+
"pad_token_id": 1,
|
48 |
+
"scale_embedding": true,
|
49 |
+
"static_position_embeddings": false,
|
50 |
+
"task_specific_params": {
|
51 |
+
"translation_en_to_ro": {
|
52 |
+
"decoder_start_token_id": 250020
|
53 |
+
}
|
54 |
+
},
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.35.2",
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 250027
|
59 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"forced_eos_token_id": 2,
|
5 |
+
"max_length": 1024,
|
6 |
+
"num_beams": 5,
|
7 |
+
"pad_token_id": 1,
|
8 |
+
"transformers_version": "4.35.2"
|
9 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c004f3d84972be0eca6d30db82e0520c25248b0b72fec5286f3b8a2827a78619
|
3 |
+
size 2444467988
|