oliviermills commited on
Commit
bd591b0
·
verified ·
1 Parent(s): 47b7ac0

Fine-tuned GLiNER2

Browse files
gliner2.5-small-passage/config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "boundary",
3
+ "architecture_version": 1,
4
+ "architectures": [
5
+ "BoundaryExtractor"
6
+ ],
7
+ "attn_implementation": "sdpa",
8
+ "boundary_head": {
9
+ "abstention_loss_weight": 0.2,
10
+ "abstention_threshold": 0.5,
11
+ "adaptive_threshold": false,
12
+ "bidirectional_proposals": true,
13
+ "boundary_attention_heads": 4,
14
+ "boundary_attention_layers": 2,
15
+ "boundary_attention_window": 128,
16
+ "boundary_dim": 128,
17
+ "boundary_ffn_multiplier": 2.0,
18
+ "boundary_focal_clip": 0.05,
19
+ "boundary_focal_gamma_negative": 2.0,
20
+ "boundary_focal_gamma_positive": 0.0,
21
+ "boundary_marginal_loss": "asymmetric_focal",
22
+ "boundary_negative_weight": 0.5,
23
+ "boundary_refinement_layers": 1,
24
+ "boundary_top_k_alpha": 0.08,
25
+ "boundary_top_k_bucket": 8,
26
+ "boundary_top_k_max": 128,
27
+ "candidate_attention_heads": 4,
28
+ "candidate_attention_layers": 0,
29
+ "candidate_budget": 192,
30
+ "candidate_pool": "shared",
31
+ "classification_loss_weight": 1.0,
32
+ "classification_temperature": 1.0,
33
+ "consistency_loss_weight": 0.1,
34
+ "consistency_warmup_steps": 2000,
35
+ "content_dim": 64,
36
+ "content_soft_max_pool": false,
37
+ "count_loss_weight": 0.2,
38
+ "directional_relation_states": true,
39
+ "dropout": 0.1,
40
+ "enable_abstention": true,
41
+ "enable_count_head": true,
42
+ "enable_records": true,
43
+ "enable_relations": true,
44
+ "enable_rotary_endpoints": true,
45
+ "enable_span_content": true,
46
+ "end_block_size": 256,
47
+ "end_top_k": 24,
48
+ "endpoint_difference_features": true,
49
+ "ends_per_start": 12,
50
+ "export_mode": "auto",
51
+ "hard_negative_keep_all_when_absent": true,
52
+ "hard_negatives_per_positive": 20,
53
+ "loss_reduction": "sum",
54
+ "max_gold_per_query": 64,
55
+ "max_negative_queries_per_batch": 64,
56
+ "min_pool_per_query": 8,
57
+ "minimum_hard_negatives": 16,
58
+ "multihead_pair_compat_heads": 8,
59
+ "negative_query_ratio": 1.0,
60
+ "overlap_policy": "flat",
61
+ "pair_dim": 128,
62
+ "pair_temperature": 1.0,
63
+ "pool_boundary_top_k": 32,
64
+ "pool_size": 192,
65
+ "proposal_loss_weight": 0.3,
66
+ "query_attention_layers": 0,
67
+ "query_conditioned_inside_weight": true,
68
+ "record_anchor_proposal_threshold": 0.2,
69
+ "record_anchor_threshold": 0.5,
70
+ "record_dim": 128,
71
+ "record_field_threshold": 0.5,
72
+ "record_instance_queries": 32,
73
+ "record_loss_weight": 1.0,
74
+ "record_temperature": 1.0,
75
+ "relation_argument_proposal_threshold": 0.2,
76
+ "relation_biaffine_content": true,
77
+ "relation_heads_per_type": 32,
78
+ "relation_loss_weight": 1.0,
79
+ "relation_pair_cap": 64,
80
+ "relation_tails_per_type": 32,
81
+ "relation_temperature": 1.0,
82
+ "rerank_listwise_weight": 0.3,
83
+ "reranker_endpoint_compat": true,
84
+ "rotary_base": 10000.0,
85
+ "soft_iou_anneal_steps": 20000,
86
+ "soft_iou_aux_weight": 0.2,
87
+ "start_top_k": 24,
88
+ "starts_per_end": 12,
89
+ "training_candidate_budget": 192,
90
+ "use_inside_evidence": true,
91
+ "vectorized_pair_elements": 16777216
92
+ },
93
+ "config_version": 3,
94
+ "max_len": 4096,
95
+ "model_name": "microsoft/deberta-v3-xsmall",
96
+ "model_type": "extractor",
97
+ "token_pooling": "first",
98
+ "transformers_version": "4.57.6"
99
+ }
gliner2.5-small-passage/encoder_config/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_probs_dropout_prob": 0.1,
3
+ "dtype": "float16",
4
+ "hidden_act": "gelu",
5
+ "hidden_dropout_prob": 0.1,
6
+ "hidden_size": 384,
7
+ "initializer_range": 0.02,
8
+ "intermediate_size": 1536,
9
+ "layer_norm_eps": 1e-07,
10
+ "legacy": true,
11
+ "max_position_embeddings": 512,
12
+ "max_relative_positions": -1,
13
+ "model_type": "deberta-v2",
14
+ "norm_rel_ebd": "layer_norm",
15
+ "num_attention_heads": 6,
16
+ "num_hidden_layers": 12,
17
+ "pad_token_id": 0,
18
+ "pooler_dropout": 0.0,
19
+ "pooler_hidden_act": "gelu",
20
+ "pooler_hidden_size": 384,
21
+ "pos_att_type": [
22
+ "p2c",
23
+ "c2p"
24
+ ],
25
+ "position_biased_input": false,
26
+ "position_buckets": 256,
27
+ "relative_attention": true,
28
+ "share_att_key": true,
29
+ "transformers_version": "4.57.6",
30
+ "type_vocab_size": 0,
31
+ "vocab_size": 128011
32
+ }
gliner2.5-small-passage/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1b918d7cb19918cffcbc3e29aef222cc8e5ce6a634dac35888637e9988b8c3
3
+ size 295567700
gliner2.5-small-passage/special_tokens_map.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "[SEP_STRUCT]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "[SEP_TEXT]",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "[P]",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "[C]",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "[E]",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "[R]",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "[L]",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "[EXAMPLE]",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "[OUTPUT]",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "[DESCRIPTION]",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ }
73
+ ],
74
+ "bos_token": {
75
+ "content": "[CLS]",
76
+ "lstrip": false,
77
+ "normalized": false,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ },
81
+ "cls_token": {
82
+ "content": "[CLS]",
83
+ "lstrip": false,
84
+ "normalized": false,
85
+ "rstrip": false,
86
+ "single_word": false
87
+ },
88
+ "eos_token": {
89
+ "content": "[SEP]",
90
+ "lstrip": false,
91
+ "normalized": false,
92
+ "rstrip": false,
93
+ "single_word": false
94
+ },
95
+ "mask_token": {
96
+ "content": "[MASK]",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": false,
100
+ "single_word": false
101
+ },
102
+ "pad_token": {
103
+ "content": "[PAD]",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false
108
+ },
109
+ "sep_token": {
110
+ "content": "[SEP]",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false
115
+ },
116
+ "unk_token": {
117
+ "content": "[UNK]",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false
122
+ }
123
+ }
gliner2.5-small-passage/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
gliner2.5-small-passage/tokenizer_config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128000": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128001": {
45
+ "content": "[SEP_STRUCT]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128002": {
53
+ "content": "[SEP_TEXT]",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128003": {
61
+ "content": "[P]",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128004": {
69
+ "content": "[C]",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128005": {
77
+ "content": "[E]",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128006": {
85
+ "content": "[R]",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128007": {
93
+ "content": "[L]",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128008": {
101
+ "content": "[EXAMPLE]",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128009": {
109
+ "content": "[OUTPUT]",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128010": {
117
+ "content": "[DESCRIPTION]",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ }
124
+ },
125
+ "additional_special_tokens": [
126
+ "[SEP_STRUCT]",
127
+ "[SEP_TEXT]",
128
+ "[P]",
129
+ "[C]",
130
+ "[E]",
131
+ "[R]",
132
+ "[L]",
133
+ "[EXAMPLE]",
134
+ "[OUTPUT]",
135
+ "[DESCRIPTION]"
136
+ ],
137
+ "backend": "tokenizers",
138
+ "bos_token": "[CLS]",
139
+ "clean_up_tokenization_spaces": false,
140
+ "cls_token": "[CLS]",
141
+ "do_lower_case": false,
142
+ "eos_token": "[SEP]",
143
+ "extra_special_tokens": {},
144
+ "is_local": true,
145
+ "local_files_only": false,
146
+ "mask_token": "[MASK]",
147
+ "model_max_length": 1000000000000000019884624838656,
148
+ "pad_token": "[PAD]",
149
+ "sep_token": "[SEP]",
150
+ "split_by_punct": false,
151
+ "tokenizer_class": "DebertaV2TokenizerFast",
152
+ "unk_id": 3,
153
+ "unk_token": "[UNK]",
154
+ "vocab_type": "spm"
155
+ }