Hugging Face's logo

shikharshahi
/
sifter-redrob-reranker

Text Classification
Transformers
Safetensors
distilbert
sifter
redrob
reranker
reward-model
recruitment
explainable-ai
human-feedback
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
shikharshahi commited on
Commit
cdc2121
·
verified ·
1 Parent(s): 26cb113

Training in progress, step 230

Browse files
Files changed (5) hide show
  1. config.json +17 -29
  2. model.safetensors +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +6 -15
  5. training_args.bin +2 -2
config.json CHANGED
@@ -1,46 +1,34 @@
1
  {
 
2
  "architectures": [
3
- "DebertaV2ForSequenceClassification"
4
  ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "bos_token_id": 1,
 
 
7
  "dtype": "float32",
8
- "eos_token_id": 2,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
  "id2label": {
13
  "0": "LABEL_0"
14
  },
15
  "initializer_range": 0.02,
16
- "intermediate_size": 3072,
17
  "label2id": {
18
  "LABEL_0": 0
19
  },
20
- "layer_norm_eps": 1e-07,
21
- "legacy": true,
22
  "max_position_embeddings": 512,
23
- "max_relative_positions": -1,
24
- "model_type": "deberta-v2",
25
- "norm_rel_ebd": "layer_norm",
26
- "num_attention_heads": 12,
27
- "num_hidden_layers": 6,
28
  "pad_token_id": 0,
29
- "pooler_dropout": 0.0,
30
- "pooler_hidden_act": "gelu",
31
- "pooler_hidden_size": 768,
32
- "pos_att_type": [
33
- "p2c",
34
- "c2p"
35
- ],
36
- "position_biased_input": false,
37
- "position_buckets": 256,
38
  "problem_type": "regression",
39
- "relative_attention": true,
40
- "share_att_key": true,
 
 
41
  "tie_word_embeddings": true,
42
- "transformers_version": "5.10.2",
43
- "type_vocab_size": 0,
44
  "use_cache": false,
45
- "vocab_size": 128100
46
  }
 
1
  {
2
+ "activation": "gelu",
3
  "architectures": [
4
+ "DistilBertForSequenceClassification"
5
  ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": null,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
  "dtype": "float32",
11
+ "eos_token_id": null,
12
+ "hidden_dim": 3072,
 
 
13
  "id2label": {
14
  "0": "LABEL_0"
15
  },
16
  "initializer_range": 0.02,
 
17
  "label2id": {
18
  "LABEL_0": 0
19
  },
 
 
20
  "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
 
 
24
  "pad_token_id": 0,
 
 
 
 
 
 
 
 
 
25
  "problem_type": "regression",
26
+ "qa_dropout": 0.1,
27
+ "seq_classif_dropout": 0.2,
28
+ "sinusoidal_pos_embds": false,
29
+ "tie_weights_": true,
30
  "tie_word_embeddings": true,
31
+ "transformers_version": "5.9.0",
 
32
  "use_cache": false,
33
+ "vocab_size": 30522
34
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75e291a2ab9284628870b72d262507a0599cb450b970b94318db51a7e6369136
3
- size 567595468
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720f8bb680cf3bba186cc7076140420dc80731f603c402ee544b80fc20a0ff9a
3
+ size 267829484
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,24 +1,15 @@
1
  {
2
- "add_prefix_space": true,
3
  "backend": "tokenizers",
4
- "bos_token": "[CLS]",
5
  "cls_token": "[CLS]",
6
- "do_lower_case": false,
7
- "eos_token": "[SEP]",
8
- "extra_special_tokens": [
9
- "[PAD]",
10
- "[CLS]",
11
- "[SEP]"
12
- ],
13
  "is_local": false,
14
  "local_files_only": false,
15
  "mask_token": "[MASK]",
16
- "model_max_length": 1000000000000000019884624838656,
17
  "pad_token": "[PAD]",
18
  "sep_token": "[SEP]",
19
- "split_by_punct": false,
20
- "tokenizer_class": "DebertaV2Tokenizer",
21
- "unk_id": 3,
22
- "unk_token": "[UNK]",
23
- "vocab_type": "spm"
24
  }
 
1
  {
 
2
  "backend": "tokenizers",
 
3
  "cls_token": "[CLS]",
4
+ "do_lower_case": true,
 
 
 
 
 
 
5
  "is_local": false,
6
  "local_files_only": false,
7
  "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
 
15
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edfa65abb0516e8eba33eddae35bbe58a30919883e68466eb64db29f198335d5
3
- size 5201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ebf36d1e70983af6f137ca4e8b77a12d819b6d5fe91ba06bb4978ce9b2f2ed7
3
+ size 5329