amiguel commited on
Commit
e1397b2
·
verified ·
1 Parent(s): 2725808

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/models/KDGPT",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2Model"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "negative": "0",
18
+ "positive": "1"
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 12,
27
+ "n_positions": 1024,
28
+ "problem_type": "single_label_classification",
29
+ "reorder_and_upcast_attn": false,
30
+ "resid_pdrop": 0.1,
31
+ "scale_attn_by_inverse_layer_idx": false,
32
+ "scale_attn_weights": true,
33
+ "summary_activation": null,
34
+ "summary_first_dropout": 0.1,
35
+ "summary_proj_to_labels": true,
36
+ "summary_type": "cls_index",
37
+ "summary_use_proj": true,
38
+ "task_specific_params": {
39
+ "text-generation": {
40
+ "do_sample": true,
41
+ "max_length": 50
42
+ }
43
+ },
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.42.4",
46
+ "use_cache": true,
47
+ "vocab_size": 50257
48
+ }
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:b6b0319df86e558d0044e991d2ae63ec54ba383961c5e01c47f778f0f275c88f
3
+ size 497772432
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50257": {
13
+ "content": "[PAD]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|endoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "eos_token": "<|endoftext|>",
24
+ "max_length": 256,
25
+ "model_max_length": 1024,
26
+ "pad_token": "[PAD]",
27
+ "stride": 0,
28
+ "tokenizer_class": "GPT2Tokenizer",
29
+ "truncation_side": "right",
30
+ "truncation_strategy": "longest_first",
31
+ "unk_token": "<|endoftext|>"
32
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff