Hugging Face's logo

webis
/
naacl25-prompt-compositions_finetune-baseline

Safetensors
Model card Files
xet
Community
mspl commited on
Commit
dea1660
·
1 Parent(s): 21e0521

Initial commit

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +32 -0
  2. models/deberta-v3-large-finetune_20240925121914_semeval-seed1337/config.json +35 -0
  3. models/deberta-v3-large-finetune_20240925121914_semeval-seed23/config.json +35 -0
  4. models/deberta-v3-large-finetune_20240925121914_semeval-seed271/config.json +35 -0
  5. models/deberta-v3-large-finetune_20240925121914_semeval-seed314/config.json +35 -0
  6. models/deberta-v3-large-finetune_20240925121914_semeval-seed42/config.json +35 -0
  7. models/deberta-v3-large-finetune_20241009160411_esnli-seed1337/config.json +35 -0
  8. models/deberta-v3-large-finetune_20241009160411_esnli-seed1337/model.safetensors +3 -0
  9. models/deberta-v3-large-finetune_20241009160411_esnli-seed1337/training_args.bin +3 -0
  10. models/deberta-v3-large-finetune_20241009160411_esnli-seed23/config.json +35 -0
  11. models/deberta-v3-large-finetune_20241009160411_esnli-seed23/model.safetensors +3 -0
  12. models/deberta-v3-large-finetune_20241009160411_esnli-seed23/training_args.bin +3 -0
  13. models/deberta-v3-large-finetune_20241009160411_esnli-seed271/config.json +35 -0
  14. models/deberta-v3-large-finetune_20241009160411_esnli-seed271/model.safetensors +3 -0
  15. models/deberta-v3-large-finetune_20241009160411_esnli-seed271/training_args.bin +3 -0
  16. models/deberta-v3-large-finetune_20241009160411_esnli-seed314/config.json +35 -0
  17. models/deberta-v3-large-finetune_20241009160411_esnli-seed314/model.safetensors +3 -0
  18. models/deberta-v3-large-finetune_20241009160411_esnli-seed314/training_args.bin +3 -0
  19. models/deberta-v3-large-finetune_20241009160411_esnli-seed42/config.json +35 -0
  20. models/deberta-v3-large-finetune_20241009160411_esnli-seed42/model.safetensors +3 -0
  21. models/deberta-v3-large-finetune_20241009160411_esnli-seed42/training_args.bin +3 -0
  22. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed1337/config.json +35 -0
  23. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed1337/model.safetensors +3 -0
  24. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed1337/training_args.bin +3 -0
  25. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed23/config.json +35 -0
  26. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed23/model.safetensors +3 -0
  27. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed23/training_args.bin +3 -0
  28. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed271/config.json +35 -0
  29. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed271/model.safetensors +3 -0
  30. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed271/training_args.bin +3 -0
  31. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed314/config.json +35 -0
  32. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed314/model.safetensors +3 -0
  33. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed314/training_args.bin +3 -0
  34. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed42/config.json +35 -0
  35. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed42/model.safetensors +3 -0
  36. models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed42/training_args.bin +3 -0
  37. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed1337/config.json +35 -0
  38. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed1337/model.safetensors +3 -0
  39. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed1337/training_args.bin +3 -0
  40. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed23/config.json +35 -0
  41. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed23/model.safetensors +3 -0
  42. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed23/training_args.bin +3 -0
  43. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed271/config.json +35 -0
  44. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed271/model.safetensors +3 -0
  45. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed271/training_args.bin +3 -0
  46. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed314/config.json +35 -0
  47. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed314/model.safetensors +3 -0
  48. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed314/training_args.bin +3 -0
  49. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed42/config.json +35 -0
  50. models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed42/model.safetensors +3 -0
README.md CHANGED
@@ -1,3 +1,35 @@
1
  ---
2
  license: cc-by-3.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: cc-by-3.0
3
  ---
4
+
5
+
6
+ Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection
7
+ =======================================================================
8
+
9
+ Finetune baseline models for the paper [Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection](https://arxiv.org/abs/2502.06487).
10
+
11
+ For details, please see the published paper and the [GitHub repository](https://github.com/webis-de/naacl25-prompt-compositions).
12
+
13
+
14
+ ```
15
+ @inproceedings{spliethover-etal-2025-adaptive,
16
+
17
+ TBDTBDTBD
18
+
19
+
20
+ title = "Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection",
21
+ author = Splieth{\"o}ver, Maximilian and Knebler, Tim and Fumagalli, Fabian and Muschalik, Maximilian and Hammer, Barbara and H{\"u}llermeier, Eyke and Wachsmuth, Henning,
22
+ booktitle = "Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics",
23
+ month = apr,
24
+ year = "2025",
25
+ address = "Albuquerque, New Mexico",
26
+ publisher = "Association for Computational Linguistics",
27
+ url = "https://arxiv.org/abs/2502.06487",
28
+ }
29
+ ```
30
+
31
+
32
+ ## Note on published models
33
+ Unfortunately, we did delete the original finetuning baseline models, for which we reported the scores in the paper. We do, however, still have the prediction results of these models.
34
+
35
+ We did retrain the models on the same splits, same seeds, same python version, and same library versions. The new models and also the new (and old) prediction results are uploaded in this repository.
models/deberta-v3-large-finetune_20240925121914_semeval-seed1337/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20240925121914_semeval-seed23/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20240925121914_semeval-seed271/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20240925121914_semeval-seed314/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20240925121914_semeval-seed42/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20241009160411_esnli-seed1337/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20241009160411_esnli-seed1337/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b96443850afa527e69d2bc814e377538eef6c49a88e1ae70b12526079ccbf8
3
+ size 1740304440
models/deberta-v3-large-finetune_20241009160411_esnli-seed1337/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3d3c6dc6b08f42451f4af2748072c718a7bbe7e06d7a8585d20cf63b1399aaf
3
+ size 6072
models/deberta-v3-large-finetune_20241009160411_esnli-seed23/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20241009160411_esnli-seed23/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:880a39cd98dbed57ed8c54a3b415259b0f3773c7c971fce51e2c7ab1544781e6
3
+ size 1740304440
models/deberta-v3-large-finetune_20241009160411_esnli-seed23/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d0312e742244e6b187ab1a75eb7f9011ad0f57826dffb664e9c6c2863c1f2a
3
+ size 6072
models/deberta-v3-large-finetune_20241009160411_esnli-seed271/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20241009160411_esnli-seed271/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bfb4f8e42ab15fa504b7860e9e5676783019d3ec195c88c1960b3cfe4e2c71f
3
+ size 1740304440
models/deberta-v3-large-finetune_20241009160411_esnli-seed271/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d82d1f396cd78cb35ae30460e34f8770dd0979ca10652d46f375b654068d27
3
+ size 6072
models/deberta-v3-large-finetune_20241009160411_esnli-seed314/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20241009160411_esnli-seed314/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6d7a605720c8cb6830a2d2427cfc05032dcd1e78ebb587d8a9d0dab381a529
3
+ size 1740304440
models/deberta-v3-large-finetune_20241009160411_esnli-seed314/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a35addca141002394ba9ac66d0ede8415b67f024d5d2f1799b5ecb1cbdae5309
3
+ size 6072
models/deberta-v3-large-finetune_20241009160411_esnli-seed42/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20241009160411_esnli-seed42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf1d1639831005acb2a23bc6704cc71ea49db79e3bc455c679f0e1b07abe212
3
+ size 1740304440
models/deberta-v3-large-finetune_20241009160411_esnli-seed42/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824899bd4313acc5bdcd6d0cb281df8b29c7547a98d0bea3fcc51ce0589cb2cb
3
+ size 6072
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed1337/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed1337/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c2affdca45e2eb1b7f14be129b2c27bb37e2e8a72e96b511b620debaddeb035
3
+ size 1740304440
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed1337/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c43633a5ea4a28d23a941d3539e3df85c5cc79b2ff9ca1517ecf1f392c411ee0
3
+ size 6072
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed23/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed23/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5983eff123cef2a32c05225aa05d5f5d39d8284b3d819cd0a60b643f96aef236
3
+ size 1740304440
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed23/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf9a544c509b36825e469bde665ac9a99a6babc742b847b88a21bf634102500
3
+ size 6072
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed271/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed271/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3b50a5a03861516069ed3be49175dfae3437edfe3a38f6b8e933d4ec41da692
3
+ size 1740304440
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed271/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9518c63f6f9fc7bcaf61d3393b86e354004d793abdc88dbca0f2d7cae3afdb5
3
+ size 6072
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed314/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed314/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f5efae4c03751e907a1310563c329e694c9ee48a14128950633f940d712300
3
+ size 1740304440
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed314/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25b867a285c5db9e07b4135195c05a0bd583569a1256abbcdb06ab4547dcbbcf
3
+ size 6072
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed42/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20b7d3be248b531f9978f4dda1c81d73e53913ffc1dc5598374012493625cf36
3
+ size 1740304440
models/deberta-v3-large-finetune_20241010181021_commonsense_qa-seed42/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcfe62ccc65106ddc2fbe5f3d5dddb7c18c1a447cfb16d37b6f0ecd4dfb04072
3
+ size 6072
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed1337/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed1337/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d472ce400e2b9d04a2350a7043db28785df1ae75c2b5bd97791ac8e85f48505
3
+ size 1740304440
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed1337/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b8766d38f9c382b29bc1685213c546503e5ee8574c732ff000639ef0b6f0f07
3
+ size 6072
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed23/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed23/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1352e061ef285f133cc47281a650d6aad039d54f0bded321b3edd3b240e93462
3
+ size 1740304440
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed23/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ce35c28b6a23ae925682382eaff4b3319741918791f2f44bf0f42d9a70232e
3
+ size 6072
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed271/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed271/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e2a48f2ca62c0a3391b2ab2cce5b266ffe136575b76889343e3d25a69797e8
3
+ size 1740304440
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed271/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f078f427406cfb7a10fe75aa5e45d3a2d3853dae7fc501461609f9cc1aa7c4e
3
+ size 6072
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed314/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed314/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a47aadda7bc6816623f8d504fb9bb7c3450dae3c49310045fe0639e06c99e5ed
3
+ size 1740304440
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed314/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab4751faf1c6139b730f1329489b578509255c9f9c1af4cb6382e897709a64d
3
+ size 6072
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed42/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
models/deberta-v3-large-finetune_20250305185342_cobra_frames-seed42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9208cdee1ff9dd49a80a3bc30090fe852b00e11ce0532219b5e4fd79ebfbc2f1
3
+ size 1740304440