hf-transformers-bot commited on
Commit
55d8eb0
·
verified ·
1 Parent(s): c240dd5

Update tiny models for GPTNeoXForSequenceClassification

Browse files
Files changed (4) hide show
  1. config.json +36 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +14 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForSequenceClassification"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "dtype": "float32",
11
+ "eos_token_id": 0,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout": 0.0,
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 64,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 37,
18
+ "is_decoder": false,
19
+ "layer_norm_eps": 1e-05,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "gpt_neox",
22
+ "num_attention_heads": 4,
23
+ "num_hidden_layers": 2,
24
+ "pad_token_id": 1,
25
+ "rope_parameters": {
26
+ "partial_rotary_factor": 0.25,
27
+ "rope_theta": 10000.0,
28
+ "rope_type": "default"
29
+ },
30
+ "tie_word_embeddings": false,
31
+ "transformers_version": "5.16.0.dev0",
32
+ "type_vocab_size": 16,
33
+ "use_cache": true,
34
+ "use_parallel_residual": true,
35
+ "vocab_size": 50277
36
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88b007f914bba2abbcd0ed22090635766a4276827a8413cdd041ea9d6bab18b5
3
+ size 13048872
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
+ "model_max_length": 512,
10
+ "pad_token": "<|padding|>",
11
+ "tokenizer_class": "GPTNeoXTokenizer",
12
+ "trim_offsets": true,
13
+ "unk_token": "<|endoftext|>"
14
+ }