Hugging Face's logo

Shabdobhedi
/
aragpt2_base_small_finetune_1

Transformers
Safetensors
Generated from Trainer
trl
sft
Model card Files
xet
 Community
Shabdobhedi commited on
Commit
4cb5f47
·
verified ·
1 Parent(s): 6b5fdf7

Training in progress, epoch 0

Browse files
Files changed (5) hide show
  1. adapter_config.json +1 -1
  2. adapter_model.safetensors +2 -2
  3. special_tokens_map.json +30 -18
  4. tokenizer_config.json +7 -0
  5. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "aubmindlab/aragpt2-base",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85096d1ab1d8a734cefb83f7b1c5ac0fa54525017bef5cc23af4b3d58fe46543
3
- size 394122560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79bd4d094684409b31a8ca16b582608fa3ce136c8250f2f638640fa5c8628591
3
+ size 888168
special_tokens_map.json CHANGED
@@ -1,22 +1,34 @@
1
  {
2
  "additional_special_tokens": [
3
- {
4
- "content": "<|im_start|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "<|im_end|>",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- }
17
  ],
18
- "bos_token": "<|im_start|>",
19
- "eos_token": "<|im_end|>",
20
- "pad_token": "<|im_end|>",
21
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  }
 
1
  {
2
  "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
 
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
  }
tokenizer_config.json CHANGED
@@ -67,8 +67,15 @@
67
  "clean_up_tokenization_spaces": false,
68
  "eos_token": "<|im_end|>",
69
  "extra_special_tokens": {},
 
70
  "model_max_length": 1000000000000000019884624838656,
 
71
  "pad_token": "<|im_end|>",
 
 
 
72
  "tokenizer_class": "GPT2Tokenizer",
 
 
73
  "unk_token": "<|endoftext|>"
74
  }
 
67
  "clean_up_tokenization_spaces": false,
68
  "eos_token": "<|im_end|>",
69
  "extra_special_tokens": {},
70
+ "max_length": 256,
71
  "model_max_length": 1000000000000000019884624838656,
72
+ "pad_to_multiple_of": null,
73
  "pad_token": "<|im_end|>",
74
+ "pad_token_type_id": 0,
75
+ "padding_side": "right",
76
+ "stride": 0,
77
  "tokenizer_class": "GPT2Tokenizer",
78
+ "truncation_side": "right",
79
+ "truncation_strategy": "longest_first",
80
  "unk_token": "<|endoftext|>"
81
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9cdd84e25f39d27cfe10e405773d6304a4e68803880b188132ee03106285a23
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c913cb47b2a62c87307eb77036b639c4407d96195796bd847f528f18fa1cd291
3
  size 5624