Jellywibble commited on
Commit
b66aefd
1 Parent(s): e64576b

Upload tokenizer

Browse files
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,41 +1,9 @@
1
  {
2
- "_name_or_path": "ChaiML/reward_models_100_170000000_cp_498032",
3
- "activation_function": "gelu_new",
4
- "architectures": [
5
- "GPT2ForSequenceClassification"
6
- ],
7
- "attn_pdrop": 0.1,
8
- "bos_token_id": 50256,
9
- "embd_pdrop": 0.1,
10
- "eos_token_id": 50256,
11
- "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_ctx": 1024,
15
- "n_embd": 768,
16
- "n_head": 12,
17
- "n_inner": null,
18
- "n_layer": 12,
19
- "n_positions": 1024,
20
- "pad_token_id": 50256,
21
- "problem_type": "single_label_classification",
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,
29
- "summary_type": "cls_index",
30
- "summary_use_proj": true,
31
- "task_specific_params": {
32
- "text-generation": {
33
- "do_sample": true,
34
- "max_length": 50
35
- }
36
- },
37
- "torch_dtype": "float32",
38
- "transformers_version": "4.30.2",
39
- "use_cache": true,
40
- "vocab_size": 50257
41
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff