nde-dilan commited on
Commit
4273cfe
·
verified ·
1 Parent(s): 28f4127

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "decoder": {
8
+ "_attn_implementation_autoset": true,
9
+ "_name_or_path": "gpt2",
10
+ "activation_function": "gelu_new",
11
+ "add_cross_attention": true,
12
+ "architectures": [
13
+ "GPT2LMHeadModel"
14
+ ],
15
+ "attn_pdrop": 0.1,
16
+ "embd_pdrop": 0.1,
17
+ "initializer_range": 0.02,
18
+ "is_decoder": true,
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "gpt2",
21
+ "n_ctx": 1024,
22
+ "n_embd": 768,
23
+ "n_head": 12,
24
+ "n_inner": null,
25
+ "n_layer": 12,
26
+ "n_positions": 1024,
27
+ "reorder_and_upcast_attn": false,
28
+ "resid_pdrop": 0.1,
29
+ "scale_attn_by_inverse_layer_idx": false,
30
+ "scale_attn_weights": true,
31
+ "summary_activation": null,
32
+ "summary_first_dropout": 0.1,
33
+ "summary_proj_to_labels": true,
34
+ "summary_type": "cls_index",
35
+ "summary_use_proj": true,
36
+ "task_specific_params": {
37
+ "text-generation": {
38
+ "do_sample": true,
39
+ "max_length": 50
40
+ }
41
+ },
42
+ "torch_dtype": "float32",
43
+ "use_cache": true,
44
+ "vocab_size": 50257
45
+ },
46
+ "decoder_start_token_id": 50256,
47
+ "dropout": 0.1,
48
+ "encoder": {
49
+ "_attn_implementation_autoset": true,
50
+ "_name_or_path": "UBC-NLP/serengeti-E250",
51
+ "architectures": [
52
+ "ElectraModel"
53
+ ],
54
+ "attention_probs_dropout_prob": 0.1,
55
+ "classifier_dropout": null,
56
+ "embedding_size": 768,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 3072,
62
+ "layer_norm_eps": 1e-12,
63
+ "max_position_embeddings": 512,
64
+ "model_type": "electra",
65
+ "num_attention_heads": 12,
66
+ "num_hidden_layers": 12,
67
+ "position_embedding_type": "absolute",
68
+ "summary_activation": "gelu",
69
+ "summary_last_dropout": 0.1,
70
+ "summary_type": "first",
71
+ "summary_use_proj": true,
72
+ "torch_dtype": "float32",
73
+ "type_vocab_size": 2,
74
+ "use_cache": true,
75
+ "vocab_size": 250000
76
+ },
77
+ "is_encoder_decoder": true,
78
+ "max_length": null,
79
+ "model_type": "encoder-decoder",
80
+ "pad_token_id": 50256,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.51.3",
83
+ "vocab_size": 50257
84
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 50256,
3
+ "decoder_start_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "max_length": 128,
6
+ "pad_token_id": 50256,
7
+ "transformers_version": "4.51.3"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aea9f568b18577dfc6c3210ad1f9a8e0b2de26679187346da963e36d8744c76
3
+ size 1721081536
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.txt ADDED
The diff for this file is too large to render. See raw diff