true merge: base+DAPT-fixed+SFT-ckpt2400
Browse files- README.md +3 -3
- config.json +1 -11
- model.safetensors +2 -2
README.md
CHANGED
|
@@ -8,12 +8,12 @@ tags:
|
|
| 8 |
- transformers
|
| 9 |
- dapt
|
| 10 |
- sft
|
| 11 |
-
model-index:
|
| 12 |
-
- name: logun-base
|
| 13 |
-
results: []
|
| 14 |
datasets:
|
| 15 |
- heitorrosa/cvm-corpus
|
| 16 |
- heitorrosa/financial-sentiment-pt
|
|
|
|
|
|
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 8 |
- transformers
|
| 9 |
- dapt
|
| 10 |
- sft
|
|
|
|
|
|
|
|
|
|
| 11 |
datasets:
|
| 12 |
- heitorrosa/cvm-corpus
|
| 13 |
- heitorrosa/financial-sentiment-pt
|
| 14 |
+
model-index:
|
| 15 |
+
- name: logun-base
|
| 16 |
+
results: []
|
| 17 |
---
|
| 18 |
|
| 19 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
@@ -19,19 +19,9 @@
|
|
| 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",
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"ModernBertModel"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
|
|
| 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",
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8444eeb1c2ab00fd195127c27f71a4eb3129d9e519dcd7de492ef86d0c35075d
|
| 3 |
+
size 596070136
|