Fill-Mask
PEFT
Safetensors
Transformers
modernbert
lora
dapt
sft
heitorrosa commited on
Commit
e000c66
·
verified ·
1 Parent(s): f74d286

merge-hero: publish final compiled model (base+DAPT+SFT-ckpt2400) to root; remove root DAPT adapter files

Browse files
adapter_config.json DELETED
@@ -1,46 +0,0 @@
1
- {
2
- "alora_invocation_tokens": null,
3
- "alpha_pattern": {},
4
- "arrow_config": null,
5
- "auto_mapping": null,
6
- "base_model_name_or_path": "Itau-Unibanco/NorBERTo-base",
7
- "bias": "none",
8
- "corda_config": null,
9
- "ensure_weight_tying": false,
10
- "eva_config": null,
11
- "exclude_modules": null,
12
- "fan_in_fan_out": false,
13
- "inference_mode": true,
14
- "init_lora_weights": true,
15
- "layer_replication": null,
16
- "layers_pattern": null,
17
- "layers_to_transform": null,
18
- "loftq_config": {},
19
- "lora_alpha": 32,
20
- "lora_bias": false,
21
- "lora_dropout": 0.05,
22
- "lora_ga_config": null,
23
- "megatron_config": null,
24
- "megatron_core": "megatron.core",
25
- "modules_to_save": null,
26
- "monteclora_config": null,
27
- "peft_type": "LORA",
28
- "peft_version": "0.20.0",
29
- "qalora_group_size": 16,
30
- "r": 16,
31
- "rank_pattern": {},
32
- "revision": null,
33
- "target_modules": [
34
- "Wo",
35
- "Wqkv",
36
- "Wi"
37
- ],
38
- "target_parameters": null,
39
- "task_type": "FEATURE_EXTRACTION",
40
- "trainable_token_indices": null,
41
- "use_bdlora": null,
42
- "use_dora": false,
43
- "use_qalora": false,
44
- "use_rslora": false,
45
- "velora_config": null
46
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa6452c598bf09450dc4e6e4e42cfd12950bcb51e453f9fc3edc3a6ce7543675
3
- size 13538528
 
 
 
 
config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "architectures": [
3
- "ModernBertForMaskedLM"
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
@@ -19,9 +19,19 @@
19
  "gradient_checkpointing": false,
20
  "hidden_activation": "gelu",
21
  "hidden_size": 768,
 
 
 
 
 
22
  "initializer_cutoff_factor": 2.0,
23
  "initializer_range": 0.02,
24
  "intermediate_size": 1152,
 
 
 
 
 
25
  "layer_norm_eps": 1e-05,
26
  "layer_types": [
27
  "full_attention",
@@ -72,6 +82,6 @@
72
  "sparse_pred_ignore_index": -100,
73
  "sparse_prediction": false,
74
  "tie_word_embeddings": true,
75
- "transformers_version": "5.15.1",
76
  "vocab_size": 50368
77
  }
 
1
  {
2
  "architectures": [
3
+ "ModernBertForSequenceClassification"
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
 
19
  "gradient_checkpointing": false,
20
  "hidden_activation": "gelu",
21
  "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "negative",
24
+ "1": "neutral",
25
+ "2": "positive"
26
+ },
27
  "initializer_cutoff_factor": 2.0,
28
  "initializer_range": 0.02,
29
  "intermediate_size": 1152,
30
+ "label2id": {
31
+ "negative": 0,
32
+ "neutral": 1,
33
+ "positive": 2
34
+ },
35
  "layer_norm_eps": 1e-05,
36
  "layer_types": [
37
  "full_attention",
 
82
  "sparse_pred_ignore_index": -100,
83
  "sparse_prediction": false,
84
  "tie_word_embeddings": true,
85
+ "transformers_version": "5.17.0",
86
  "vocab_size": 50368
87
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c24c4b16d1f9ab60f630e6d7265be39093f750c6b71bfea7dfbb8621f1239838
3
- size 598635032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ea1c5a2103418ff8abbbb966fb248f58f3f1e2f64df23c4c533588e0cf48c5
3
+ size 598442860