Ahmade commited on
Commit
ca8abb8
·
1 Parent(s): 1bc0a47
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<bos>": 50257,
3
+ "<eos>": 50258,
4
+ "<pad>": 50259,
5
+ "<speaker1>": 50260,
6
+ "<speaker2>": 50261
7
+ }
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gorkemgoknar/gpt2chatbotenglish",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "eos_token_ids": null,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "output_past": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.26.1",
39
+ "use_cache": true,
40
+ "vocab_size": 50262
41
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.26.1"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8dd8100f5698ae65780c96a145aebfcb1608d1d16184cc651e26621df1b6aea
3
+ size 510413373
runs/Feb24_12-21-25_7307d23572ba/1677241300.9295022/events.out.tfevents.1677241300.7307d23572ba.24055.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76201463ac26aa94a479458ad5649cdb682e74e8e679a1de11c4a52ae8fd1377
3
+ size 5887
runs/Feb24_12-21-25_7307d23572ba/events.out.tfevents.1677241300.7307d23572ba.24055.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ce82a53d6b9c5af21d5aa7614b5f8b43d3a7e5e7005f1a8f79dd1b34d4ab88
3
+ size 4595
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<speaker1>",
4
+ "<speaker2>"
5
+ ],
6
+ "bos_token": "<bos>",
7
+ "eos_token": "<eos>",
8
+ "pad_token": "<pad>",
9
+ "unk_token": "<|endoftext|>"
10
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "additional_special_tokens": [
5
+ "<speaker1>",
6
+ "<speaker2>"
7
+ ],
8
+ "bos_token": {
9
+ "__type": "AddedToken",
10
+ "content": "<bos>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "__type": "AddedToken",
18
+ "content": "<eos>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "errors": "replace",
25
+ "max_len": 1024,
26
+ "model_max_length": 1024,
27
+ "name_or_path": "gorkemgoknar/gpt2chatbotenglish",
28
+ "pad_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<pad>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--gorkemgoknar--gpt2chatbotenglish/snapshots/d18684a4d566c2e7f2acdd164415bd7533e8290d/special_tokens_map.json",
37
+ "tokenizer_class": "GPT2Tokenizer",
38
+ "unk_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<|endoftext|>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ }
46
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b11b567371997d6aa915a39292eddb57c6a4a6b55ad7b4bc9f7ded34ff0ea53
3
+ size 3579
vocab.json ADDED
The diff for this file is too large to render. See raw diff