Upload folder using huggingface_hub
Browse files- added_tokens.json +6 -0
- config.json +3 -0
- gliner_config.json +45 -0
- onnx/model.onnx +3 -0
- onnx/model_bnb4.onnx +3 -0
- onnx/model_fp16.onnx +3 -0
- onnx/model_int8.onnx +3 -0
- onnx/model_q4.onnx +3 -0
- onnx/model_q4f16.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- onnx/model_uint8.onnx +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +82 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<<ENT>>": 128002,
|
| 3 |
+
"<<SEP>>": 128003,
|
| 4 |
+
"[FLERT]": 128001,
|
| 5 |
+
"[MASK]": 128000
|
| 6 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "gliner"
|
| 3 |
+
}
|
gliner_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"class_token_index": 128002,
|
| 3 |
+
"dropout": 0.1,
|
| 4 |
+
"encoder_config": null,
|
| 5 |
+
"ent_token": "<<ENT>>",
|
| 6 |
+
"eval_every": 2500,
|
| 7 |
+
"fine_tune": true,
|
| 8 |
+
"freeze_token_rep": false,
|
| 9 |
+
"gpu": "pds@a100",
|
| 10 |
+
"has_rnn": true,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"log_dir": "/gpfsdswork/projects/rech/bwq/upa43yu/gliner-pip/train_gliner/token_gliner_ft_logs/deberta-v3-base_0",
|
| 13 |
+
"loss_alpha": -1,
|
| 14 |
+
"loss_gamma": 0,
|
| 15 |
+
"loss_reduction": "sum",
|
| 16 |
+
"lr_encoder": "1e-6",
|
| 17 |
+
"lr_others": "1e-6",
|
| 18 |
+
"max_len": 384,
|
| 19 |
+
"max_neg_type_ratio": 1,
|
| 20 |
+
"max_types": 25,
|
| 21 |
+
"max_width": 100,
|
| 22 |
+
"model_name": "microsoft/deberta-v3-base",
|
| 23 |
+
"model_type": "gliner",
|
| 24 |
+
"name": "token level gliner",
|
| 25 |
+
"num_steps": 30000,
|
| 26 |
+
"prev_path": "/gpfswork/rech/bwq/upa43yu/gliner-pip/train_gliner/token_gliner_logs/deberta-v3-base_4/model_30000",
|
| 27 |
+
"random_drop": true,
|
| 28 |
+
"root_dir": "token_gliner_ft_logs",
|
| 29 |
+
"run_time": "3:30:00",
|
| 30 |
+
"scheduler_type": "cosine",
|
| 31 |
+
"sep_token": "<<SEP>>",
|
| 32 |
+
"shuffle_types": true,
|
| 33 |
+
"size_sup": -1,
|
| 34 |
+
"span_mode": "token_level",
|
| 35 |
+
"subtoken_pooling": "first",
|
| 36 |
+
"train_batch_size": 8,
|
| 37 |
+
"train_data": "/gpfswork/rech/bwq/upa43yu/gliner-pip/train_gliner/train_new.json",
|
| 38 |
+
"transformers_version": "4.38.2",
|
| 39 |
+
"val_data_dir": "/gpfswork/rech/ohy/upa43yu/NER_datasets",
|
| 40 |
+
"vocab_size": 128004,
|
| 41 |
+
"warmup_ratio": 0.1,
|
| 42 |
+
"weight_decay_encoder": 0.01,
|
| 43 |
+
"weight_decay_other": 0.01,
|
| 44 |
+
"words_splitter_type": "whitespace"
|
| 45 |
+
}
|
onnx/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38758b49ba990b4af95beb99cc8e694bf1956a31b0d63b5d2eab729bb6ff5aaf
|
| 3 |
+
size 788345450
|
onnx/model_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:920ea567134848041ae9630e861e6add520439dfe4709d4eddd7976824fa813b
|
| 3 |
+
size 526444645
|
onnx/model_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb6cfc92801b2feaf07ca9ce592e5fbf794c646d68530e1705ada2dc6e0604f4
|
| 3 |
+
size 395318518
|
onnx/model_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3c9bb18677bc618873f92cf8fcefdf74830aee210df6f401699fe2075ec6286
|
| 3 |
+
size 256899553
|
onnx/model_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:920ea567134848041ae9630e861e6add520439dfe4709d4eddd7976824fa813b
|
| 3 |
+
size 526444645
|
onnx/model_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6741cb08893418823a2c8f1b35ef81323f79e737a705a95472f6c27194c2048d
|
| 3 |
+
size 287948535
|
onnx/model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3c9bb18677bc618873f92cf8fcefdf74830aee210df6f401699fe2075ec6286
|
| 3 |
+
size 256899553
|
onnx/model_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f362972b371f6c6e6669f0c3cf3ca6098cf3b30a1f38611415fc1b53be1a16f5
|
| 3 |
+
size 256899590
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128001": {
|
| 44 |
+
"content": "[FLERT]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"128002": {
|
| 52 |
+
"content": "<<ENT>>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"128003": {
|
| 60 |
+
"content": "<<SEP>>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
}
|
| 67 |
+
},
|
| 68 |
+
"bos_token": "[CLS]",
|
| 69 |
+
"clean_up_tokenization_spaces": true,
|
| 70 |
+
"cls_token": "[CLS]",
|
| 71 |
+
"do_lower_case": false,
|
| 72 |
+
"eos_token": "[SEP]",
|
| 73 |
+
"mask_token": "[MASK]",
|
| 74 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 75 |
+
"pad_token": "[PAD]",
|
| 76 |
+
"sep_token": "[SEP]",
|
| 77 |
+
"sp_model_kwargs": {},
|
| 78 |
+
"split_by_punct": false,
|
| 79 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 80 |
+
"unk_token": "[UNK]",
|
| 81 |
+
"vocab_type": "spm"
|
| 82 |
+
}
|