theabdulsaboor commited on
Commit
fc55c70
·
verified ·
1 Parent(s): ab541ee

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "openai-community/gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
1
  {
2
+ "_name_or_path": "theabdulsaboor/gpt2-therapist-finetuned",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eb84af9500ca8d6545128db8f9a0cbbfa616bd1527a132ad4f73699b7991dbe
3
  size 497777280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020d8f64192331b5759bfef408f7159b1d5d8b3c4205fe111a27dc16a4acec44
3
  size 497777280
special_tokens_map.json CHANGED
@@ -1,6 +1,18 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
4
  "pad_token": {
5
  "content": "[PAD]",
6
  "lstrip": false,
@@ -8,5 +20,11 @@
8
  "rstrip": false,
9
  "single_word": false
10
  },
11
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
12
  }
 
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,
 
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_config.json CHANGED
@@ -21,8 +21,15 @@
21
  "bos_token": "<|endoftext|>",
22
  "clean_up_tokenization_spaces": false,
23
  "eos_token": "<|endoftext|>",
 
24
  "model_max_length": 1024,
 
25
  "pad_token": "[PAD]",
 
 
 
26
  "tokenizer_class": "GPT2Tokenizer",
 
 
27
  "unk_token": "<|endoftext|>"
28
  }
 
21
  "bos_token": "<|endoftext|>",
22
  "clean_up_tokenization_spaces": false,
23
  "eos_token": "<|endoftext|>",
24
+ "max_length": 512,
25
  "model_max_length": 1024,
26
+ "pad_to_multiple_of": null,
27
  "pad_token": "[PAD]",
28
+ "pad_token_type_id": 0,
29
+ "padding_side": "right",
30
+ "stride": 0,
31
  "tokenizer_class": "GPT2Tokenizer",
32
+ "truncation_side": "right",
33
+ "truncation_strategy": "longest_first",
34
  "unk_token": "<|endoftext|>"
35
  }