IvoHoese commited on
Commit
094d139
·
verified ·
1 Parent(s): 6f0551b

Upload folder using huggingface_hub

Browse files
models/pythia-fulltuning/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForSequenceClassification"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "dtype": "float32",
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "is_decoder": false,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2
26
+ },
27
+ "layer_norm_eps": 1e-05,
28
+ "max_position_embeddings": 2048,
29
+ "model_type": "gpt_neox",
30
+ "num_attention_heads": 16,
31
+ "num_hidden_layers": 24,
32
+ "pad_token_id": 0,
33
+ "problem_type": "single_label_classification",
34
+ "rope_parameters": {
35
+ "partial_rotary_factor": 0.25,
36
+ "rope_theta": 10000,
37
+ "rope_type": "default"
38
+ },
39
+ "tie_word_embeddings": false,
40
+ "transformers_version": "5.1.0",
41
+ "use_cache": false,
42
+ "use_parallel_residual": true,
43
+ "vocab_size": 50304
44
+ }
models/pythia-fulltuning/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2eb3937da9d12d9ac47742896393a89ec9f1e93bcd5cc61f536da0ad4105e4
3
+ size 1415337224
models/pythia-fulltuning/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models/pythia-fulltuning/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 1000000000000000019884624838656,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "GPTNeoXTokenizer",
11
+ "trim_offsets": true,
12
+ "unk_token": "<|endoftext|>"
13
+ }