Instructions to use tolga-ozturk/mGPT-nsp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tolga-ozturk/mGPT-nsp with Transformers:
# Load model directly from transformers import AutoTokenizer, ModelNSP tokenizer = AutoTokenizer.from_pretrained("tolga-ozturk/mGPT-nsp") model = ModelNSP.from_pretrained("tolga-ozturk/mGPT-nsp") - Notebooks
- Google Colab
- Kaggle
Commit ·
0963459
1
Parent(s): b939fa8
Upload config.json
Browse files- config.json +2 -2
config.json
CHANGED
|
@@ -1,8 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"_num_labels": 2,
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
"attn_pdrop": 0.1,
|
| 8 |
"bos_token_id": 1,
|
|
@@ -27,6 +26,7 @@
|
|
| 27 |
"summary_proj_to_labels": true,
|
| 28 |
"summary_type": "cls_index",
|
| 29 |
"summary_use_proj": true,
|
|
|
|
| 30 |
"transformers_version": "4.18.0",
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 250100
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_function": "gelu_new",
|
| 3 |
"architectures": [
|
| 4 |
+
"ModelNSP"
|
| 5 |
],
|
| 6 |
"attn_pdrop": 0.1,
|
| 7 |
"bos_token_id": 1,
|
|
|
|
| 26 |
"summary_proj_to_labels": true,
|
| 27 |
"summary_type": "cls_index",
|
| 28 |
"summary_use_proj": true,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
"transformers_version": "4.18.0",
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 250100
|