Hugging Face's logo

danielkty22
/
gpt-neo-125m-lr-0.0001-bs-16-wd-0.001-e-0.5-multi_model-peft-bitfit

Question Answering
Transformers
Safetensors
gpt_neo
Inference Endpoints
Model card Files Community
danielkty22 commited on
Commit
08c6721
•
1 Parent(s): 32606f6

Training in progress, epoch 0

Browse files
Files changed (8) hide show
  1. config.json +55 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +37 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +23 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125m",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForQuestionAnswering"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "classifier_dropout": 0.1,
33
+ "embed_dropout": 0,
34
+ "eos_token_id": 50256,
35
+ "gradient_checkpointing": false,
36
+ "hidden_size": 768,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": null,
39
+ "layer_norm_epsilon": 1e-05,
40
+ "max_position_embeddings": 2048,
41
+ "model_type": "gpt_neo",
42
+ "num_heads": 12,
43
+ "num_layers": 12,
44
+ "resid_dropout": 0,
45
+ "summary_activation": null,
46
+ "summary_first_dropout": 0.1,
47
+ "summary_proj_to_labels": true,
48
+ "summary_type": "cls_index",
49
+ "summary_use_proj": true,
50
+ "torch_dtype": "bfloat16",
51
+ "transformers_version": "4.43.3",
52
+ "use_cache": true,
53
+ "vocab_size": 50257,
54
+ "window_size": 256
55
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa9c3038f89c7ea31f0622aad818e33dfdfcfa112e63ef56c9438a2408f82e8
3
+ size 250417444
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 2048,
19
+ "pad_token": "<|endoftext|>",
20
+ "sep_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84a09e32116633e1001968d9126d9dff45bdbfe74ee414890dd0d0483b1e38bb
3
+ size 5368
vocab.json ADDED
The diff for this file is too large to render. See raw diff