adetuire1 commited on
Commit
f95bf2c
·
verified ·
1 Parent(s): 060681c

Add fine-tuned GPT-2 weights + tokenizer

Browse files
config.json CHANGED
@@ -32,7 +32,7 @@
32
  }
33
  },
34
  "torch_dtype": "float32",
35
- "transformers_version": "4.54.1",
36
  "use_cache": true,
37
  "vocab_size": 50257
38
  }
 
32
  }
33
  },
34
  "torch_dtype": "float32",
35
+ "transformers_version": "4.55.0",
36
  "use_cache": true,
37
  "vocab_size": 50257
38
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
- "transformers_version": "4.54.1"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
+ "transformers_version": "4.55.0"
6
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:516d0eed5745ed9af1aecfdd5777309af3163bdc3c6c20b0e0666daac0492993
3
+ size 497774208
special_tokens_map.json CHANGED
@@ -1,23 +1,5 @@
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
- "unk_token": {
17
- "content": "<|endoftext|>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "add_bos_token": false,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
  "50256": {
@@ -14,10 +13,8 @@
14
  "bos_token": "<|endoftext|>",
15
  "clean_up_tokenization_spaces": false,
16
  "eos_token": "<|endoftext|>",
17
- "errors": "replace",
18
  "extra_special_tokens": {},
19
  "model_max_length": 1024,
20
- "pad_token": null,
21
  "tokenizer_class": "GPT2Tokenizer",
22
  "unk_token": "<|endoftext|>"
23
  }
 
1
  {
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "50256": {
 
13
  "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": false,
15
  "eos_token": "<|endoftext|>",
 
16
  "extra_special_tokens": {},
17
  "model_max_length": 1024,
 
18
  "tokenizer_class": "GPT2Tokenizer",
19
  "unk_token": "<|endoftext|>"
20
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff