Instructions to use heitorrosa/logun-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use heitorrosa/logun-base with PEFT:
Task type is invalid.
- Transformers
How to use heitorrosa/logun-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="heitorrosa/logun-base")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("heitorrosa/logun-base") model = AutoModelForMaskedLM.from_pretrained("heitorrosa/logun-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
revert root to standalone DAPT full weights (0.7042-verified, no adapters)
Browse files- config.json +2 -2
- model.safetensors +2 -2
- tokenizer.json +2 -14
- training_args.bin +0 -3
config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
@@ -72,6 +72,6 @@
|
|
| 72 |
"sparse_pred_ignore_index": -100,
|
| 73 |
"sparse_prediction": false,
|
| 74 |
"tie_word_embeddings": true,
|
| 75 |
-
"transformers_version": "5.
|
| 76 |
"vocab_size": 50368
|
| 77 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"ModernBertForMaskedLM"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
|
|
| 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 |
}
|
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:c24c4b16d1f9ab60f630e6d7265be39093f750c6b71bfea7dfbb8621f1239838
|
| 3 |
+
size 598635032
|
tokenizer.json
CHANGED
|
@@ -1,19 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 128,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": "BatchLongest",
|
| 11 |
-
"direction": "Right",
|
| 12 |
-
"pad_to_multiple_of": null,
|
| 13 |
-
"pad_id": 5,
|
| 14 |
-
"pad_type_id": 0,
|
| 15 |
-
"pad_token": "[PAD]"
|
| 16 |
-
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:526d6f5586cc12f8c3c2decff856ac271e872bdfd30bb3aeb82e6bca21f6e912
|
| 3 |
-
size 5265
|
|
|
|
|
|
|
|
|
|
|
|