Thomas Dehaene commited on
Commit
937ba9e
1 Parent(s): c0dc10e

Initial commit

Browse files
Files changed (5) hide show
  1. config.json +32 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +1 -0
  4. tokenizer_config.json +1 -0
  5. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "resid_pdrop": 0.1,
20
+ "summary_activation": null,
21
+ "summary_first_dropout": 0.1,
22
+ "summary_proj_to_labels": true,
23
+ "summary_type": "cls_index",
24
+ "summary_use_proj": true,
25
+ "task_specific_params": {
26
+ "text-generation": {
27
+ "do_sample": true,
28
+ "max_length": 50
29
+ }
30
+ },
31
+ "vocab_size": 50257
32
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"pad_token": "<|endoftext|>", "special_tokens_map_file": null, "full_tokenizer_file": null}
vocab.json ADDED
The diff for this file is too large to render. See raw diff