Upload folder using huggingface_hub
Browse files- gliner_config.json +17 -15
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +6 -42
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- trainer_state.json +0 -0
gliner_config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
|
|
2 |
"class_token_index": -1,
|
3 |
-
"dropout": 0.
|
4 |
"embed_ent_token": true,
|
5 |
"encoder_config": {
|
6 |
"_name_or_path": "microsoft/deberta-v3-base",
|
@@ -91,7 +92,8 @@
|
|
91 |
"vocab_size": 128100
|
92 |
},
|
93 |
"ent_token": "<<ENT>>",
|
94 |
-
"
|
|
|
95 |
"fine_tune": true,
|
96 |
"freeze_token_rep": false,
|
97 |
"fuse_layers": false,
|
@@ -177,40 +179,40 @@
|
|
177 |
"use_cache": true,
|
178 |
"vocab_size": 30522
|
179 |
},
|
180 |
-
"log_dir": "
|
181 |
"loss_alpha": 0.8,
|
182 |
"loss_gamma": 2,
|
183 |
"loss_reduction": "sum",
|
184 |
"lr_encoder": "1e-5",
|
185 |
"lr_others": "5e-5",
|
186 |
"max_grad_norm": 10.0,
|
187 |
-
"max_len":
|
188 |
-
"max_neg_type_ratio":
|
189 |
-
"max_types":
|
190 |
"max_width": 12,
|
191 |
"model_name": "microsoft/deberta-v3-base",
|
192 |
"model_type": "gliner",
|
193 |
-
"name": "span level gliner",
|
194 |
"num_post_fusion_layers": 1,
|
195 |
-
"num_steps":
|
196 |
"post_fusion_schema": "",
|
197 |
"prev_path": null,
|
198 |
"random_drop": true,
|
199 |
"root_dir": "gliner_logs",
|
200 |
-
"save_total_limit":
|
201 |
"scheduler_type": "cosine",
|
202 |
"sep_token": "<<SEP>>",
|
203 |
"shuffle_types": true,
|
204 |
"size_sup": -1,
|
205 |
"span_mode": "markerV0",
|
206 |
"subtoken_pooling": "first",
|
207 |
-
"train_batch_size":
|
208 |
-
"train_data": "
|
209 |
"transformers_version": "4.45.2",
|
210 |
-
"val_data_dir":
|
211 |
"vocab_size": -1,
|
212 |
-
"warmup_ratio": 0.
|
213 |
-
"weight_decay_encoder": 0.
|
214 |
-
"weight_decay_other": 0.
|
215 |
"words_splitter_type": "whitespace"
|
216 |
}
|
|
|
1 |
{
|
2 |
+
"blank_prompt_rep_layer": true,
|
3 |
"class_token_index": -1,
|
4 |
+
"dropout": 0.36,
|
5 |
"embed_ent_token": true,
|
6 |
"encoder_config": {
|
7 |
"_name_or_path": "microsoft/deberta-v3-base",
|
|
|
92 |
"vocab_size": 128100
|
93 |
},
|
94 |
"ent_token": "<<ENT>>",
|
95 |
+
"entity_linking": null,
|
96 |
+
"eval_every": 2000,
|
97 |
"fine_tune": true,
|
98 |
"freeze_token_rep": false,
|
99 |
"fuse_layers": false,
|
|
|
179 |
"use_cache": true,
|
180 |
"vocab_size": 30522
|
181 |
},
|
182 |
+
"log_dir": "models-base/",
|
183 |
"loss_alpha": 0.8,
|
184 |
"loss_gamma": 2,
|
185 |
"loss_reduction": "sum",
|
186 |
"lr_encoder": "1e-5",
|
187 |
"lr_others": "5e-5",
|
188 |
"max_grad_norm": 10.0,
|
189 |
+
"max_len": 768,
|
190 |
+
"max_neg_type_ratio": 5,
|
191 |
+
"max_types": 256,
|
192 |
"max_width": 12,
|
193 |
"model_name": "microsoft/deberta-v3-base",
|
194 |
"model_type": "gliner",
|
195 |
+
"name": "span level gliner for entity linking",
|
196 |
"num_post_fusion_layers": 1,
|
197 |
+
"num_steps": 250000,
|
198 |
"post_fusion_schema": "",
|
199 |
"prev_path": null,
|
200 |
"random_drop": true,
|
201 |
"root_dir": "gliner_logs",
|
202 |
+
"save_total_limit": 20,
|
203 |
"scheduler_type": "cosine",
|
204 |
"sep_token": "<<SEP>>",
|
205 |
"shuffle_types": true,
|
206 |
"size_sup": -1,
|
207 |
"span_mode": "markerV0",
|
208 |
"subtoken_pooling": "first",
|
209 |
+
"train_batch_size": 4,
|
210 |
+
"train_data": "final_dataset_1m.json",
|
211 |
"transformers_version": "4.45.2",
|
212 |
+
"val_data_dir": null,
|
213 |
"vocab_size": -1,
|
214 |
+
"warmup_ratio": 0.1,
|
215 |
+
"weight_decay_encoder": 0.01,
|
216 |
+
"weight_decay_other": 0.02,
|
217 |
"words_splitter_type": "whitespace"
|
218 |
}
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1909053417
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d715bc24d43bc12d4495df9052db1a26c603409be463330444d10aab5e06a6f
|
3 |
size 1909053417
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 969281034
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0bb20d34cbf8143ca9dc32ed449c360a6dc34cfb2a19383360acd194344450e
|
3 |
size 969281034
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2245ff461e27bd85ebe7cf50effd201369973673cfc345f1fa7e0b8fa1aa7602
|
3 |
size 14244
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15170f8dedcb512efd0826216d18529f578fcb9cf778e78614bfe3c54ac40dde
|
3 |
size 1064
|
special_tokens_map.json
CHANGED
@@ -1,46 +1,10 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
},
|
9 |
-
"cls_token": {
|
10 |
-
"content": "[CLS]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"eos_token": {
|
17 |
-
"content": "[SEP]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"mask_token": {
|
24 |
-
"content": "[MASK]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"pad_token": {
|
31 |
-
"content": "[PAD]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
},
|
37 |
-
"sep_token": {
|
38 |
-
"content": "[SEP]",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false
|
43 |
-
},
|
44 |
"unk_token": {
|
45 |
"content": "[UNK]",
|
46 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
"unk_token": {
|
9 |
"content": "[UNK]",
|
10 |
"lstrip": false,
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -42,7 +42,7 @@
|
|
42 |
}
|
43 |
},
|
44 |
"bos_token": "[CLS]",
|
45 |
-
"clean_up_tokenization_spaces":
|
46 |
"cls_token": "[CLS]",
|
47 |
"do_lower_case": false,
|
48 |
"eos_token": "[SEP]",
|
|
|
42 |
}
|
43 |
},
|
44 |
"bos_token": "[CLS]",
|
45 |
+
"clean_up_tokenization_spaces": false,
|
46 |
"cls_token": "[CLS]",
|
47 |
"do_lower_case": false,
|
48 |
"eos_token": "[SEP]",
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|