sandip shrestha commited on
Commit
eb6393d
·
verified ·
1 Parent(s): fcc3ebc

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "pad_token_id": null,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "tie_word_embeddings": true,
31
+ "transformers_version": "5.0.0",
32
+ "use_cache": true,
33
+ "vocab_size": 50257
34
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.0.0",
8
+ "use_cache": true
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b93df760cf7c6b76eaa7ff318aed740dd7c293668dcb68b38c4856f2979a69
3
+ size 652163920
tokenizer.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|endoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ }
15
+ ],
16
+ "normalizer": null,
17
+ "pre_tokenizer": {
18
+ "type": "ByteLevel",
19
+ "add_prefix_space": false,
20
+ "trim_offsets": true,
21
+ "use_regex": true
22
+ },
23
+ "post_processor": {
24
+ "type": "TemplateProcessing",
25
+ "single": [
26
+ {
27
+ "Sequence": {
28
+ "id": "A",
29
+ "type_id": 0
30
+ }
31
+ }
32
+ ],
33
+ "pair": [
34
+ {
35
+ "Sequence": {
36
+ "id": "A",
37
+ "type_id": 0
38
+ }
39
+ },
40
+ {
41
+ "Sequence": {
42
+ "id": "B",
43
+ "type_id": 1
44
+ }
45
+ }
46
+ ],
47
+ "special_tokens": {}
48
+ },
49
+ "decoder": {
50
+ "type": "ByteLevel",
51
+ "add_prefix_space": true,
52
+ "trim_offsets": true,
53
+ "use_regex": true
54
+ },
55
+ "model": {
56
+ "type": "BPE",
57
+ "dropout": null,
58
+ "unk_token": null,
59
+ "continuing_subword_prefix": "",
60
+ "end_of_word_suffix": "",
61
+ "fuse_unk": false,
62
+ "byte_fallback": false,
63
+ "ignore_merges": false,
64
+ "vocab": {},
65
+ "merges": []
66
+ }
67
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": true,
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "pad_token": null,
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }