Push model using huggingface_hub.
Browse files- gliner_config.json +46 -0
- special_tokens_map.json +42 -6
- tokenizer.json +0 -0
gliner_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"class_token_index": 128001,
|
| 3 |
+
"dropout": 0.4,
|
| 4 |
+
"encoder_config": null,
|
| 5 |
+
"ent_token": "<<ENT>>",
|
| 6 |
+
"eval_every": 3000,
|
| 7 |
+
"fine_tune": true,
|
| 8 |
+
"freeze_token_rep": false,
|
| 9 |
+
"has_rnn": true,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"label_smoothing": 0,
|
| 12 |
+
"log_dir": "meals-gliner",
|
| 13 |
+
"loss_alpha": -1,
|
| 14 |
+
"loss_gamma": 0,
|
| 15 |
+
"loss_reduction": "sum",
|
| 16 |
+
"lr_encoder": "1e-5",
|
| 17 |
+
"lr_others": "5e-5",
|
| 18 |
+
"max_grad_norm": 1.0,
|
| 19 |
+
"max_len": 384,
|
| 20 |
+
"max_neg_type_ratio": 1,
|
| 21 |
+
"max_types": 25,
|
| 22 |
+
"max_width": 12,
|
| 23 |
+
"model_name": "microsoft/deberta-v3-small",
|
| 24 |
+
"model_type": "gliner",
|
| 25 |
+
"name": "span level gliner",
|
| 26 |
+
"num_steps": 30000,
|
| 27 |
+
"prev_path": "none",
|
| 28 |
+
"random_drop": true,
|
| 29 |
+
"root_dir": "gliner_logs",
|
| 30 |
+
"save_total_limit": 10,
|
| 31 |
+
"scheduler_type": "cosine",
|
| 32 |
+
"sep_token": "<<SEP>>",
|
| 33 |
+
"shuffle_types": true,
|
| 34 |
+
"size_sup": -1,
|
| 35 |
+
"span_mode": "markerV0",
|
| 36 |
+
"subtoken_pooling": "first",
|
| 37 |
+
"train_batch_size": 8,
|
| 38 |
+
"train_data": "meal_data.json",
|
| 39 |
+
"transformers_version": "4.41.2",
|
| 40 |
+
"val_data_dir": "none",
|
| 41 |
+
"vocab_size": 128003,
|
| 42 |
+
"warmup_ratio": 0.1,
|
| 43 |
+
"weight_decay_encoder": 0.01,
|
| 44 |
+
"weight_decay_other": 0.01,
|
| 45 |
+
"words_splitter_type": "whitespace"
|
| 46 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -1,10 +1,46 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"unk_token": {
|
| 9 |
"content": "[UNK]",
|
| 10 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 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,
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|