AmirMalekhosseini commited on
Commit
76ac11c
·
verified ·
1 Parent(s): ec4213b

Upload folder using huggingface_hub

Browse files
tiny-gpt2/pretrained/config.json CHANGED
@@ -1,10 +1,12 @@
1
  {
2
  "activation_function": "gelu_new",
 
3
  "architectures": [
4
  "GPT2LMHeadModel"
5
  ],
6
  "attn_pdrop": 0.1,
7
  "bos_token_id": 50256,
 
8
  "embd_pdrop": 0.1,
9
  "eos_token_id": 50256,
10
  "initializer_range": 0.02,
@@ -13,9 +15,14 @@
13
  "n_ctx": 1024,
14
  "n_embd": 2,
15
  "n_head": 2,
 
16
  "n_layer": 2,
17
  "n_positions": 1024,
 
 
18
  "resid_pdrop": 0.1,
 
 
19
  "summary_activation": null,
20
  "summary_first_dropout": 0.1,
21
  "summary_proj_to_labels": true,
@@ -27,5 +34,8 @@
27
  "max_length": 50
28
  }
29
  },
 
 
 
30
  "vocab_size": 50257
31
  }
 
1
  {
2
  "activation_function": "gelu_new",
3
+ "add_cross_attention": false,
4
  "architectures": [
5
  "GPT2LMHeadModel"
6
  ],
7
  "attn_pdrop": 0.1,
8
  "bos_token_id": 50256,
9
+ "dtype": "float32",
10
  "embd_pdrop": 0.1,
11
  "eos_token_id": 50256,
12
  "initializer_range": 0.02,
 
15
  "n_ctx": 1024,
16
  "n_embd": 2,
17
  "n_head": 2,
18
+ "n_inner": null,
19
  "n_layer": 2,
20
  "n_positions": 1024,
21
+ "pad_token_id": null,
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,
 
34
  "max_length": 50
35
  }
36
  },
37
+ "tie_word_embeddings": true,
38
+ "transformers_version": "5.14.1",
39
+ "use_cache": true,
40
  "vocab_size": 50257
41
  }
tiny-gpt2/pretrained/tokenizer_config.json CHANGED
@@ -1 +1,13 @@
1
- {"model_max_length": 1024}
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1024,
10
+ "pad_token": null,
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }