l3utterfly commited on
Commit
9e44600
·
verified ·
1 Parent(s): a3252bc

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "BartForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 0,
11
+ "classif_dropout": 0.0,
12
+ "classifier_dropout": 0.0,
13
+ "d_model": 1024,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 4096,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 12,
18
+ "decoder_start_token_id": 2,
19
+ "dropout": 0.1,
20
+ "dtype": "float32",
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
+ "force_bos_token_to_be_generated": true,
27
+ "forced_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_decoder": false,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "normalize_before": false,
45
+ "output_past": true,
46
+ "pad_token_id": 1,
47
+ "prefix": " ",
48
+ "scale_embedding": false,
49
+ "task_specific_params": {
50
+ "summarization": {
51
+ "early_stopping": true,
52
+ "length_penalty": 2.0,
53
+ "max_length": 142,
54
+ "min_length": 56,
55
+ "no_repeat_ngram_size": 3,
56
+ "num_beams": 4
57
+ }
58
+ },
59
+ "tie_word_embeddings": true,
60
+ "transformers_version": "5.9.0",
61
+ "use_cache": false,
62
+ "vocab_size": 50264
63
+ }
generation_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": false,
3
+ "assistant_confidence_threshold": 0.4,
4
+ "assistant_lookbehind": 10,
5
+ "bos_token_id": 0,
6
+ "decoder_start_token_id": 2,
7
+ "diversity_penalty": 0.0,
8
+ "do_sample": false,
9
+ "early_stopping": true,
10
+ "encoder_no_repeat_ngram_size": 0,
11
+ "encoder_repetition_penalty": 1.0,
12
+ "eos_token_id": [
13
+ 2
14
+ ],
15
+ "epsilon_cutoff": 0.0,
16
+ "eta_cutoff": 0.0,
17
+ "forced_bos_token_id": 0,
18
+ "forced_eos_token_id": 2,
19
+ "length_penalty": 2.0,
20
+ "max_length": 256,
21
+ "min_length": 30,
22
+ "no_repeat_ngram_size": 3,
23
+ "num_assistant_tokens": 20,
24
+ "num_assistant_tokens_schedule": "constant",
25
+ "num_beam_groups": 1,
26
+ "num_beams": 4,
27
+ "num_return_sequences": 1,
28
+ "output_scores": false,
29
+ "pad_token_id": 1,
30
+ "remove_invalid_values": false,
31
+ "repetition_penalty": 1.0,
32
+ "return_dict_in_generate": false,
33
+ "target_lookbehind": 10,
34
+ "temperature": 1.0,
35
+ "top_k": 50,
36
+ "top_p": 1.0,
37
+ "transformers_version": "5.9.0",
38
+ "typical_p": 1.0,
39
+ "use_cache": true
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aae9ba217edac9fa2bc3a12aab9c7eb080570e710bdfc8d8c2ace8a97b183da
3
+ size 1625422896
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "mask_token": "<mask>",
11
+ "model_max_length": 1024,
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "tokenizer_class": "RobertaTokenizer",
15
+ "trim_offsets": true,
16
+ "unk_token": "<unk>"
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f4042645f7d1a63f0cd2182c746028539ff69d2329f821b149481f71c790a2
3
+ size 5393