Hugging Face's logo

arampacha
/
gpt-neo-therapist-small

Text Generation
Transformers
PyTorch
TensorBoard
ONNX
gpt_neo
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
2
arampacha commited on
Commit
4635110
•
1 Parent(s): a8e2f90

End of training

Browse files
Files changed (17) hide show
  1. .gitignore +1 -0
  2. config.json +54 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. runs/Mar30_08-42-54_e1bd325e9b71/1648630966.7963965/events.out.tfevents.1648630966.e1bd325e9b71.69.1 +3 -0
  6. runs/Mar30_08-42-54_e1bd325e9b71/events.out.tfevents.1648630966.e1bd325e9b71.69.0 +3 -0
  7. runs/Mar30_09-22-17_e1bd325e9b71/1648632160.617431/events.out.tfevents.1648632160.e1bd325e9b71.2698.1 +3 -0
  8. runs/Mar30_09-22-17_e1bd325e9b71/events.out.tfevents.1648632160.e1bd325e9b71.2698.0 +3 -0
  9. runs/Mar30_09-42-05_e1bd325e9b71/1648634444.5432656/events.out.tfevents.1648634444.e1bd325e9b71.2992.3 +3 -0
  10. runs/Mar30_09-42-05_e1bd325e9b71/events.out.tfevents.1648633385.e1bd325e9b71.2992.0 +3 -0
  11. runs/Mar30_09-42-05_e1bd325e9b71/events.out.tfevents.1648634316.e1bd325e9b71.2992.1 +3 -0
  12. runs/Mar30_09-42-05_e1bd325e9b71/events.out.tfevents.1648634444.e1bd325e9b71.2992.2 +3 -0
  13. special_tokens_map.json +1 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +1 -0
  16. training_args.bin +3 -0
  17. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125M",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
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
+ "embed_dropout": 0,
33
+ "eos_token_id": 50256,
34
+ "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.17.0",
51
+ "use_cache": false,
52
+ "vocab_size": 50257,
53
+ "window_size": 256
54
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a5a347ab23cb63e59d80e36950ef55cfc2eee29b2f0565605a83bd023b9e3be
3
+ size 551195601
runs/Mar30_08-42-54_e1bd325e9b71/1648630966.7963965/events.out.tfevents.1648630966.e1bd325e9b71.69.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98ae2d2bc31a2de4025cc39cf4fbfdd41064fbaea5594c938a11ef8ddf359e3f
3
+ size 4785
runs/Mar30_08-42-54_e1bd325e9b71/events.out.tfevents.1648630966.e1bd325e9b71.69.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b515b610116db0e9b5195f1837fc058c7612e3ff14370b73c9a30c71d10cfaec
3
+ size 3877
runs/Mar30_09-22-17_e1bd325e9b71/1648632160.617431/events.out.tfevents.1648632160.e1bd325e9b71.2698.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6203a6751b0e964313647ecf8fa61168081d9cace920e552a2f006c531462706
3
+ size 4785
runs/Mar30_09-22-17_e1bd325e9b71/events.out.tfevents.1648632160.e1bd325e9b71.2698.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:238c00f560ee8223230388b7eca8519413d0b5fed3fd25d3db22a4d998bf0f45
3
+ size 3878
runs/Mar30_09-42-05_e1bd325e9b71/1648634444.5432656/events.out.tfevents.1648634444.e1bd325e9b71.2992.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af1dc98d476fb2dbc2dce7cafd5839e0d9f015a97f0e003eb928a4fa80c1c292
3
+ size 4785
runs/Mar30_09-42-05_e1bd325e9b71/events.out.tfevents.1648633385.e1bd325e9b71.2992.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3947b68624b0b4a15e4c3fc337d50ee8bb23ae21fb7ab58ac4a5d1c4488726b8
3
+ size 249
runs/Mar30_09-42-05_e1bd325e9b71/events.out.tfevents.1648634316.e1bd325e9b71.2992.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9590d7ce4ef10eacb34b00fca2cfb379d7583b349d7a0755b15f95e501f015fd
3
+ size 488
runs/Mar30_09-42-05_e1bd325e9b71/events.out.tfevents.1648634444.e1bd325e9b71.2992.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebbbf2dce85ee7fc191f1eaa7ad3b68ec476705cfe36553ec7edf31adb2490b2
3
+ size 7725
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-125M", "tokenizer_class": "GPT2Tokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84fac99440d3a2720e8ea04424f7061cd785562afdad70947b87071cb582ceb2
3
+ size 3055
vocab.json ADDED
The diff for this file is too large to render. See raw diff