Hugging Face's logo

m3hrdadfi
/
MoGPT-experiments-dd-medium

TensorBoard
Model card Files Metrics Community
m3hrdadfi commited on
Commit
f8e9ff4
•
1 Parent(s): d4f6cdb

Push medium dd version

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. dd-umb-gpt2-medium-context/.gitattributes +34 -0
  2. dd-umb-gpt2-medium-context/.gitignore +1 -0
  3. dd-umb-gpt2-medium-context/added_tokens.json +10 -0
  4. dd-umb-gpt2-medium-context/config.json +50 -0
  5. dd-umb-gpt2-medium-context/epoch_last.ckpt +3 -0
  6. dd-umb-gpt2-medium-context/logs/dd-umb-gpt2-medium-context/version_02-02-2023--16-55-57/events.out.tfevents.1675353359.alvis3-14 +3 -0
  7. dd-umb-gpt2-medium-context/logs/dd-umb-gpt2-medium-context/version_02-02-2023--16-55-57/events.out.tfevents.1675356629.alvis3-14 +3 -0
  8. dd-umb-gpt2-medium-context/logs/dd-umb-gpt2-medium-context/version_02-02-2023--16-55-57/hparams.yaml +0 -0
  9. dd-umb-gpt2-medium-context/merges.txt +0 -0
  10. dd-umb-gpt2-medium-context/outputs/epoch_end.json +0 -0
  11. dd-umb-gpt2-medium-context/pytorch_model.bin +3 -0
  12. dd-umb-gpt2-medium-context/special_tokens_map.json +13 -0
  13. dd-umb-gpt2-medium-context/tokenizer.json +0 -0
  14. dd-umb-gpt2-medium-context/tokenizer_config.json +10 -0
  15. dd-umb-gpt2-medium-context/vocab.json +0 -0
  16. dd-umt-gpt2-medium-context/.gitattributes +34 -0
  17. dd-umt-gpt2-medium-context/.gitignore +1 -0
  18. dd-umt-gpt2-medium-context/added_tokens.json +10 -0
  19. dd-umt-gpt2-medium-context/config.json +50 -0
  20. dd-umt-gpt2-medium-context/epoch_last.ckpt +3 -0
  21. dd-umt-gpt2-medium-context/logs/dd-umt-gpt2-medium-context/version_01-02-2023--23-54-10/events.out.tfevents.1675292053.alvis4-35 +3 -0
  22. dd-umt-gpt2-medium-context/logs/dd-umt-gpt2-medium-context/version_01-02-2023--23-54-10/events.out.tfevents.1675295451.alvis4-35 +3 -0
  23. dd-umt-gpt2-medium-context/logs/dd-umt-gpt2-medium-context/version_01-02-2023--23-54-10/hparams.yaml +0 -0
  24. dd-umt-gpt2-medium-context/merges.txt +0 -0
  25. dd-umt-gpt2-medium-context/outputs/epoch_end.json +0 -0
  26. dd-umt-gpt2-medium-context/pytorch_model.bin +3 -0
  27. dd-umt-gpt2-medium-context/special_tokens_map.json +13 -0
  28. dd-umt-gpt2-medium-context/tokenizer.json +0 -0
  29. dd-umt-gpt2-medium-context/tokenizer_config.json +10 -0
  30. dd-umt-gpt2-medium-context/vocab.json +0 -0
  31. dd-urb-gpt2-medium-context/.gitattributes +34 -0
  32. dd-urb-gpt2-medium-context/.gitignore +1 -0
  33. dd-urb-gpt2-medium-context/added_tokens.json +10 -0
  34. dd-urb-gpt2-medium-context/config.json +50 -0
  35. dd-urb-gpt2-medium-context/epoch_last.ckpt +3 -0
  36. dd-urb-gpt2-medium-context/logs/dd-urb-gpt2-medium-context/version_01-02-2023--23-53-32/events.out.tfevents.1675292015.alvis4-34 +3 -0
  37. dd-urb-gpt2-medium-context/logs/dd-urb-gpt2-medium-context/version_01-02-2023--23-53-32/events.out.tfevents.1675295288.alvis4-34 +3 -0
  38. dd-urb-gpt2-medium-context/logs/dd-urb-gpt2-medium-context/version_01-02-2023--23-53-32/hparams.yaml +0 -0
  39. dd-urb-gpt2-medium-context/merges.txt +0 -0
  40. dd-urb-gpt2-medium-context/outputs/epoch_end.json +0 -0
  41. dd-urb-gpt2-medium-context/pytorch_model.bin +3 -0
  42. dd-urb-gpt2-medium-context/special_tokens_map.json +13 -0
  43. dd-urb-gpt2-medium-context/tokenizer.json +0 -0
  44. dd-urb-gpt2-medium-context/tokenizer_config.json +10 -0
  45. dd-urb-gpt2-medium-context/vocab.json +0 -0
  46. dd-urt-gpt2-medium-context/.gitattributes +34 -0
  47. dd-urt-gpt2-medium-context/.gitignore +1 -0
  48. dd-urt-gpt2-medium-context/added_tokens.json +10 -0
  49. dd-urt-gpt2-medium-context/config.json +50 -0
  50. dd-urt-gpt2-medium-context/epoch_last.ckpt +3 -0
dd-umb-gpt2-medium-context/.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
dd-umb-gpt2-medium-context/.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ step*
dd-umb-gpt2-medium-context/added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<bos>": 50257,
3
+ "<context>": 50263,
4
+ "<dialog>": 50264,
5
+ "<eos>": 50258,
6
+ "<mask>": 50260,
7
+ "<pad>": 50259,
8
+ "<persona>": 50262,
9
+ "<sep>": 50261
10
+ }
dd-umb-gpt2-medium-context/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2DoubleHeadsModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "aux_num_labels": 3,
9
+ "bos_token_id": 50257,
10
+ "class_names": [],
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 50258,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 1024,
24
+ "n_head": 16,
25
+ "n_inner": null,
26
+ "n_layer": 24,
27
+ "n_positions": 1024,
28
+ "n_special": 0,
29
+ "pad_token_id": 50259,
30
+ "predict_special_tokens": true,
31
+ "reorder_and_upcast_attn": false,
32
+ "resid_pdrop": 0.1,
33
+ "scale_attn_by_inverse_layer_idx": false,
34
+ "scale_attn_weights": true,
35
+ "summary_activation": null,
36
+ "summary_first_dropout": 0.1,
37
+ "summary_proj_to_labels": true,
38
+ "summary_type": "cls_index",
39
+ "summary_use_proj": true,
40
+ "task_specific_params": {
41
+ "text-generation": {
42
+ "do_sample": true,
43
+ "max_length": 50
44
+ }
45
+ },
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.25.1",
48
+ "use_cache": true,
49
+ "vocab_size": 50265
50
+ }
dd-umb-gpt2-medium-context/epoch_last.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:814848a5f41c64124cb2e4d53f1654a5665ee858f5a06a86f52232d5ef21dfe2
3
+ size 4297680015
dd-umb-gpt2-medium-context/logs/dd-umb-gpt2-medium-context/version_02-02-2023--16-55-57/events.out.tfevents.1675353359.alvis3-14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c91da81d5a02ad46e1121ebad83ceb931b8e1b88a56466c2c7ca4363e7bcd6
3
+ size 109379
dd-umb-gpt2-medium-context/logs/dd-umb-gpt2-medium-context/version_02-02-2023--16-55-57/events.out.tfevents.1675356629.alvis3-14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d02cf36cab6ebae1bbf31e1cefacf5ab68f370ca94178600bce719b272bfad
3
+ size 1746
dd-umb-gpt2-medium-context/logs/dd-umb-gpt2-medium-context/version_02-02-2023--16-55-57/hparams.yaml ADDED
The diff for this file is too large to render. See raw diff
 
dd-umb-gpt2-medium-context/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
dd-umb-gpt2-medium-context/outputs/epoch_end.json ADDED
The diff for this file is too large to render. See raw diff
 
dd-umb-gpt2-medium-context/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b343f32c276d9a7281125f0f3d3e9942af0137c294ae7f7d0a8fd38091a6dfcc
3
+ size 1448823093
dd-umb-gpt2-medium-context/special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<sep>",
4
+ "<persona>",
5
+ "<context>",
6
+ "<dialog>"
7
+ ],
8
+ "bos_token": "<bos>",
9
+ "eos_token": "<eos>",
10
+ "mask_token": "<mask>",
11
+ "pad_token": "<pad>",
12
+ "unk_token": "<|endoftext|>"
13
+ }
dd-umb-gpt2-medium-context/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
dd-umb-gpt2-medium-context/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "gpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
dd-umb-gpt2-medium-context/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
dd-umt-gpt2-medium-context/.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
dd-umt-gpt2-medium-context/.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ step*
dd-umt-gpt2-medium-context/added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<bos>": 50257,
3
+ "<context>": 50263,
4
+ "<dialog>": 50264,
5
+ "<eos>": 50258,
6
+ "<mask>": 50260,
7
+ "<pad>": 50259,
8
+ "<persona>": 50262,
9
+ "<sep>": 50261
10
+ }
dd-umt-gpt2-medium-context/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2DoubleHeadsModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "aux_num_labels": 50265,
9
+ "bos_token_id": 50257,
10
+ "class_names": [],
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 50258,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 1024,
24
+ "n_head": 16,
25
+ "n_inner": null,
26
+ "n_layer": 24,
27
+ "n_positions": 1024,
28
+ "n_special": 0,
29
+ "pad_token_id": 50259,
30
+ "predict_special_tokens": true,
31
+ "reorder_and_upcast_attn": false,
32
+ "resid_pdrop": 0.1,
33
+ "scale_attn_by_inverse_layer_idx": false,
34
+ "scale_attn_weights": true,
35
+ "summary_activation": null,
36
+ "summary_first_dropout": 0.1,
37
+ "summary_proj_to_labels": true,
38
+ "summary_type": "cls_index",
39
+ "summary_use_proj": true,
40
+ "task_specific_params": {
41
+ "text-generation": {
42
+ "do_sample": true,
43
+ "max_length": 50
44
+ }
45
+ },
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.25.1",
48
+ "use_cache": true,
49
+ "vocab_size": 50265
50
+ }
dd-umt-gpt2-medium-context/epoch_last.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f1dd720a4ac00c008355ebd264724452bffe7cd6d9fd47e601d933bcf1bb0a
3
+ size 4915905503
dd-umt-gpt2-medium-context/logs/dd-umt-gpt2-medium-context/version_01-02-2023--23-54-10/events.out.tfevents.1675292053.alvis4-35 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8835df48ae08c10b67132abbb22fecd202029ebe409ee590197d7e4fbfc1ad
3
+ size 109379
dd-umt-gpt2-medium-context/logs/dd-umt-gpt2-medium-context/version_01-02-2023--23-54-10/events.out.tfevents.1675295451.alvis4-35 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea23e67217fe9364512d2de45bc615011c58ef569e97a48d9517247da464f5e
3
+ size 1746
dd-umt-gpt2-medium-context/logs/dd-umt-gpt2-medium-context/version_01-02-2023--23-54-10/hparams.yaml ADDED
The diff for this file is too large to render. See raw diff
 
dd-umt-gpt2-medium-context/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
dd-umt-gpt2-medium-context/outputs/epoch_end.json ADDED
The diff for this file is too large to render. See raw diff
 
dd-umt-gpt2-medium-context/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d07baf4e1bea5e1ff02d30ff53846950a9565ae0a4191d5acd5d3ff3021ab344
3
+ size 1654897269
dd-umt-gpt2-medium-context/special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<sep>",
4
+ "<persona>",
5
+ "<context>",
6
+ "<dialog>"
7
+ ],
8
+ "bos_token": "<bos>",
9
+ "eos_token": "<eos>",
10
+ "mask_token": "<mask>",
11
+ "pad_token": "<pad>",
12
+ "unk_token": "<|endoftext|>"
13
+ }
dd-umt-gpt2-medium-context/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
dd-umt-gpt2-medium-context/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "gpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
dd-umt-gpt2-medium-context/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
dd-urb-gpt2-medium-context/.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
dd-urb-gpt2-medium-context/.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ step*
dd-urb-gpt2-medium-context/added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<bos>": 50257,
3
+ "<context>": 50263,
4
+ "<dialog>": 50264,
5
+ "<eos>": 50258,
6
+ "<mask>": 50260,
7
+ "<pad>": 50259,
8
+ "<persona>": 50262,
9
+ "<sep>": 50261
10
+ }
dd-urb-gpt2-medium-context/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2DoubleHeadsModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "aux_num_labels": 2,
9
+ "bos_token_id": 50257,
10
+ "class_names": [],
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 50258,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 1024,
24
+ "n_head": 16,
25
+ "n_inner": null,
26
+ "n_layer": 24,
27
+ "n_positions": 1024,
28
+ "n_special": 0,
29
+ "pad_token_id": 50259,
30
+ "predict_special_tokens": true,
31
+ "reorder_and_upcast_attn": false,
32
+ "resid_pdrop": 0.1,
33
+ "scale_attn_by_inverse_layer_idx": false,
34
+ "scale_attn_weights": true,
35
+ "summary_activation": null,
36
+ "summary_first_dropout": 0.1,
37
+ "summary_proj_to_labels": true,
38
+ "summary_type": "cls_index",
39
+ "summary_use_proj": true,
40
+ "task_specific_params": {
41
+ "text-generation": {
42
+ "do_sample": true,
43
+ "max_length": 50
44
+ }
45
+ },
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.25.1",
48
+ "use_cache": true,
49
+ "vocab_size": 50265
50
+ }
dd-urb-gpt2-medium-context/epoch_last.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2028b4353d56ae07644d35d54a490ba981a142fb6cb246dcdd2713981c7c0375
3
+ size 4297667663
dd-urb-gpt2-medium-context/logs/dd-urb-gpt2-medium-context/version_01-02-2023--23-53-32/events.out.tfevents.1675292015.alvis4-34 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:111a87e1a50f14a6d644d6c634480c856fc7c12bc5282e59c50f46b4f53f7c5b
3
+ size 109379
dd-urb-gpt2-medium-context/logs/dd-urb-gpt2-medium-context/version_01-02-2023--23-53-32/events.out.tfevents.1675295288.alvis4-34 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:480ea531e240a2249f46a32553210289ee4b075660ad88f61c2e55b18b53238d
3
+ size 1746
dd-urb-gpt2-medium-context/logs/dd-urb-gpt2-medium-context/version_01-02-2023--23-53-32/hparams.yaml ADDED
The diff for this file is too large to render. See raw diff
 
dd-urb-gpt2-medium-context/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
dd-urb-gpt2-medium-context/outputs/epoch_end.json ADDED
The diff for this file is too large to render. See raw diff
 
dd-urb-gpt2-medium-context/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e7ee0e6776001f70ef0432e31b2a899272a94af33ca0a3f7fa6d88b573ee3b5
3
+ size 1448818997
dd-urb-gpt2-medium-context/special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<sep>",
4
+ "<persona>",
5
+ "<context>",
6
+ "<dialog>"
7
+ ],
8
+ "bos_token": "<bos>",
9
+ "eos_token": "<eos>",
10
+ "mask_token": "<mask>",
11
+ "pad_token": "<pad>",
12
+ "unk_token": "<|endoftext|>"
13
+ }
dd-urb-gpt2-medium-context/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
dd-urb-gpt2-medium-context/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "gpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
dd-urb-gpt2-medium-context/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
dd-urt-gpt2-medium-context/.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
dd-urt-gpt2-medium-context/.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ step*
dd-urt-gpt2-medium-context/added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<bos>": 50257,
3
+ "<context>": 50263,
4
+ "<dialog>": 50264,
5
+ "<eos>": 50258,
6
+ "<mask>": 50260,
7
+ "<pad>": 50259,
8
+ "<persona>": 50262,
9
+ "<sep>": 50261
10
+ }
dd-urt-gpt2-medium-context/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2DoubleHeadsModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "aux_num_labels": 50265,
9
+ "bos_token_id": 50257,
10
+ "class_names": [],
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 50258,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 1024,
24
+ "n_head": 16,
25
+ "n_inner": null,
26
+ "n_layer": 24,
27
+ "n_positions": 1024,
28
+ "n_special": 0,
29
+ "pad_token_id": 50259,
30
+ "predict_special_tokens": true,
31
+ "reorder_and_upcast_attn": false,
32
+ "resid_pdrop": 0.1,
33
+ "scale_attn_by_inverse_layer_idx": false,
34
+ "scale_attn_weights": true,
35
+ "summary_activation": null,
36
+ "summary_first_dropout": 0.1,
37
+ "summary_proj_to_labels": true,
38
+ "summary_type": "cls_index",
39
+ "summary_use_proj": true,
40
+ "task_specific_params": {
41
+ "text-generation": {
42
+ "do_sample": true,
43
+ "max_length": 50
44
+ }
45
+ },
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.25.1",
48
+ "use_cache": true,
49
+ "vocab_size": 50265
50
+ }
dd-urt-gpt2-medium-context/epoch_last.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89fa13d36d635539bf948015522169c6e2517bac131ecf8aa505988330f567f
3
+ size 4915905439