BharathP08 commited on
Commit
3c41535
·
verified ·
1 Parent(s): 2410c6d

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "LEDForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_window": [
9
+ 1024,
10
+ 1024,
11
+ 1024,
12
+ 1024,
13
+ 1024,
14
+ 1024
15
+ ],
16
+ "bos_token_id": 0,
17
+ "classif_dropout": 0.0,
18
+ "classifier_dropout": 0.0,
19
+ "d_model": 768,
20
+ "decoder_attention_heads": 12,
21
+ "decoder_ffn_dim": 3072,
22
+ "decoder_layerdrop": 0.0,
23
+ "decoder_layers": 6,
24
+ "decoder_start_token_id": 2,
25
+ "dropout": 0.1,
26
+ "dtype": "float16",
27
+ "encoder_attention_heads": 12,
28
+ "encoder_ffn_dim": 3072,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 6,
31
+ "eos_token_id": 2,
32
+ "gradient_checkpointing": false,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1",
36
+ "2": "LABEL_2"
37
+ },
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_2": 2
44
+ },
45
+ "max_decoder_position_embeddings": 1024,
46
+ "max_encoder_position_embeddings": 16384,
47
+ "model_type": "led",
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "tie_word_embeddings": true,
51
+ "transformers_version": "5.1.0",
52
+ "use_cache": false,
53
+ "vocab_size": 50265
54
+ }
generation_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
10
+ "encoder_no_repeat_ngram_size": 0,
11
+ "encoder_repetition_penalty": 1.0,
12
+ "eos_token_id": 2,
13
+ "epsilon_cutoff": 0.0,
14
+ "eta_cutoff": 0.0,
15
+ "length_penalty": 1.0,
16
+ "max_length": 20,
17
+ "min_length": 0,
18
+ "no_repeat_ngram_size": 0,
19
+ "num_assistant_tokens": 20,
20
+ "num_assistant_tokens_schedule": "constant",
21
+ "num_beam_groups": 1,
22
+ "num_beams": 1,
23
+ "num_return_sequences": 1,
24
+ "output_scores": false,
25
+ "pad_token_id": 1,
26
+ "remove_invalid_values": false,
27
+ "repetition_penalty": 1.0,
28
+ "return_dict_in_generate": false,
29
+ "target_lookbehind": 10,
30
+ "temperature": 1.0,
31
+ "top_k": 50,
32
+ "top_p": 1.0,
33
+ "transformers_version": "5.1.0",
34
+ "typical_p": 1.0,
35
+ "use_cache": true
36
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fa429aca20e00b16006b883133f500a633e2c03251c4e04164651ea98bf82b0
3
+ size 555446138
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "mask_token": "<mask>",
10
+ "model_max_length": 16384,
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }